AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE
Benchmark Radar.Benchmarks. Model results. Original sources.
/

Artificial Analysis

Humanity’s Last Exam

Humanity’s Last Exam tests expert-level academic knowledge and reasoning. This page preserves Artificial Analysis’s collected model results, with the original benchmark and date meanings explained below.

Official projectOriginal paperOfficial datasetOfficial repositoryCatalog source

AI Benchmark Radar / Equality Machine · Reviewed 2026-10-29

The Artificial Analysis results collected on 25 August 2026. Original HLE publications and current methodology are linked for context; later revisions do not establish each saved run’s setup.

Expert questions across academic subjects

Developed by the Center for AI Safety and Scale AI with expert contributors, HLE combines multiple-choice and short-answer questions across mathematics, humanities and the natural sciences. The original project links its paper, dataset and evaluation code. Artificial Analysis conducts its own evaluations; its results remain distinct from the original authors’ leaderboard.

Humanity’s Last Exam · original project · Humanity’s Last Exam · paper and version history · Artificial Analysis · Humanity’s Last Exam evaluation

Release, collection and model dates

The public benchmark announcement is dated 23 January 2025; the first arXiv submission is dated 24 January. This record was collected on 25 August 2026. Dates beside individual results are model announcement dates, labelled as a model release proxy, not the dates those evaluations were run. The captured source does not provide per-run dates.

Scale AI and CAIS · public announcement dated 23 January 2025 · Humanity’s Last Exam · paper and version history · AI Benchmark Radar · saved record, collection timestamp and row date basis

Keep the model configuration attached

Model names retain the source’s version, reasoning-effort and fallback labels where supplied. Rows also retain the source’s model identity. A display name does not establish an immutable provider API revision; that revision was not supplied in the captured table. Units and per-run protocols that were not recorded remain unknown, and the original numeric values are preserved.

AI Benchmark Radar · saved record, collection timestamp and row date basis · Artificial Analysis · Humanity’s Last Exam evaluation

Read current methodology with the snapshot date

The methodology reviewed on 29 October is v5.0 and describes HLE as 2,158 text-only questions from the May 2025 revision, scored with pass@1. It treats HLE-Diamond separately. This provides context, not verified historical settings for every saved row. Do not substitute today’s grader, dataset revision or leaderboard values for the captured results.

Artificial Analysis · current methodology, reviewed 29 October 2026 · AI Benchmark Radar · saved record, collection timestamp and row date basis

Original publication

Original Humanity’s Last Exam publications for this Artificial Analysis source record. Scores remain the separately collected Artificial Analysis snapshot from 25 August 2026; later publication and dataset revisions do not establish the setup of every saved evaluation.

Reviewed 2026-10-29

Evidence available for this benchmark

This source record contains 577 numeric observations. The source distinguishes 577 model identities or configurations. A model may appear more than once; check the version, tools and run budget before comparing. Read results and row-level evidence →

Metric direction
higher is better

Start with these resources

Cited documents and dates (1)

Catalog collected on 2026-08-25; resources and fields reflect that saved source.

Evaluation context and evidence

Source
Artificial Analysis
Publisher
Not recorded
Benchmark release
2025-01-23
Collected
2026-08-25
Modality
Not recorded

These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.

Reported results 577

Shown in source observation order, not ranked. Dates retain the precision provided by the source.

ModelValueUnitProtocolReported date and basisSource
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)0.554680259499537Not recordedNot recorded2026-06-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Max Effort)0.548656163113994Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)0.544022242817424Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, High Effort)0.528266913809083Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Medium Effort)0.512974976830398Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
GPT-5.6 Sol (max)0.494902687673772Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)0.486561631139944Not recordedNot recorded2026-05-28 · model_announcementArtificial Analysis
Gemini 3.7 Flash (high)0.478683966635774Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
GPT-5.6 Sol (xhigh)0.473123262279889Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemini 3.1 Pro Preview0.470342910101946Not recordedNot recorded2026-02-19 · model_announcementArtificial Analysis
Kimi K3 (max)0.468952734012975Not recordedNot recorded2026-07-16 · model_announcementArtificial Analysis
Muse Spark 1.1 (xhigh)0.462001853568119Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Sol (high)0.46014828544949Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.5 (xhigh)0.457831325301205Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Muse Spark 1.2 (xhigh)0.454587581093605Not recordedNot recorded2026-08-05 · model_announcementArtificial Analysis
GPT-5.5 (high)0.450417052826691Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.6 (xhigh)0.440685820203893Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.4 (xhigh)0.437442075996293Not recordedNot recorded2026-03-05 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Low Effort)0.434198331788693Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Qwen3.8 Max0.430491195551437Not recordedNot recorded2026-08-03 · model_announcementArtificial Analysis
GPT-5.6 Terra (max)0.429101019462465Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok 4.6 (high)0.429101019462465Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Gemini 3.5 Flash (high)0.42678405931418Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
Grok 4.5 (high)0.42678405931418Not recordedNot recorded2026-07-08 · model_announcementArtificial Analysis
GPT-5.3 Codex (xhigh)0.424930491195551Not recordedNot recorded2026-02-05 · model_announcementArtificial Analysis
Qwen3.8 2.4T A95B0.424467099165894Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.5 (medium)0.42354031510658Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)0.423076923076923Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
GLM-5.3 (max)0.422613531047266Not recordedNot recorded2026-08-18 · model_announcementArtificial Analysis
GPT-5.6 Sol (medium)0.422150139017609Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok 4.6 (medium)0.421223354958295Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.6 Terra (xhigh)0.418906394810009Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemini 3.5 Flash (medium)0.413345690454124Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)0.412882298424467Not recordedNot recorded2026-06-30 · model_announcementArtificial Analysis
GLM-5.2 (max)0.411492122335496Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)0.410101946246525Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
Gemini 3.6 Flash (high)0.408248378127896Not recordedNot recorded2026-07-21 · model_announcementArtificial Analysis
Muse Spark0.406858202038925Not recordedNot recorded2026-04-08 · model_announcementArtificial Analysis
Qwen3.7 Max0.405004633920297Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
Motif 3 (Beta)0.403614457831325Not recordedNot recorded2026-07-14 · model_announcementArtificial Analysis
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)0.399443929564411Not recordedNot recorded2026-02-05 · model_announcementArtificial Analysis
Gemini 3 Pro Preview (high)0.397126969416126Not recordedNot recorded2025-11-18 · model_announcementArtificial Analysis
GPT-5.6 Luna (max)0.394810009267841Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Sol (low)0.393883225208526Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
MiniMax-M30.389712696941613Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
Gemini 3.7 Flash (medium)0.389712696941613Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)0.385542168674699Not recordedNot recorded2026-07-31 · model_announcementArtificial Analysis
GPT-5.6 Terra (high)0.385078776645042Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok Build 0.1 06160.382761816496756Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
GPT-5.2 (xhigh)0.376737720111214Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, Max Effort)0.375347544022243Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Kimi K2.60.374884151992586Not recordedNot recorded2026-04-20 · model_announcementArtificial Analysis
Grok 4.3 (high)0.372103799814643Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
GPT-5.6 Luna (xhigh)0.369786839666358Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Motif 30.369786839666358Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Gemini 3 Flash Preview (Reasoning)0.365616311399444Not recordedNot recorded2025-12-17 · model_announcementArtificial Analysis
GPT-5.2 Codex (xhigh)0.357275254865616Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
MiMo-V2.5-Pro0.356811862835959Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
Qwen3.7 Plus0.356348470806302Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, High Effort)0.352177942539388Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Gemini 3.7 Flash (low)0.351251158480074Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
Kimi K2.7 Code0.35032437442076Not recordedNot recorded2026-06-12 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, Max Effort)0.348470806302132Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Grok 4.20 0309 v2 (Reasoning)0.345227062094532Not recordedNot recorded2026-04-07 · model_announcementArtificial Analysis
DeepSeek V4 Flash Vision (Reasoning, Max Effort)0.344763670064875Not recordedNot recorded2026-08-21 · model_announcementArtificial Analysis
Qwen3.8 27B (xhigh)0.33920296570899Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Nex-N2-Pro0.337349397590361Not recordedNot recorded2026-06-02 · model_announcementArtificial Analysis
LongCat 2.00.336886005560704Not recordedNot recorded2026-06-29 · model_announcementArtificial Analysis
KAT-Coder-Pro V10.336422613531047Not recordedNot recorded2025-11-11 · model_announcementArtificial Analysis
Agnes 2.5 Pro Alpha0.33595922150139Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)0.33595922150139Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
Hy30.334569045412419Not recordedNot recorded2026-07-06 · model_announcementArtificial Analysis
GPT-5.6 Luna (high)0.334105653382762Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 4.7 (Non-reasoning, High Effort)0.333178869323448Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
Inkling Small0.333178869323448Not recordedNot recorded2026-07-30 · model_announcementArtificial Analysis
GPT-5.6 Terra (medium)0.332715477293791Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.5 (low)0.326691380908248Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.20 0309 (Reasoning)0.323911028730306Not recordedNot recorded2026-03-10 · model_announcementArtificial Analysis
Inkling (xhigh)0.318813716404078Not recordedNot recorded2026-07-15 · model_announcementArtificial Analysis
GPT-5.4 (low)0.308155699721965Not recordedNot recorded2026-03-05 · model_announcementArtificial Analysis
Qwen3.6 Max Preview0.308155699721965Not recordedNot recorded2026-04-20 · model_announcementArtificial Analysis
Kimi K2.5 (Reasoning)0.307228915662651Not recordedNot recorded2026-01-27 · model_announcementArtificial Analysis
MiMo-V2-Pro0.304448563484708Not recordedNot recorded2026-03-18 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, High Effort)0.30259499536608Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Claude Opus 4.5 (Reasoning)0.301204819277108Not recordedNot recorded2025-11-24 · model_announcementArtificial Analysis
GLM-5.1 (Reasoning)0.300741427247451Not recordedNot recorded2026-04-07 · model_announcementArtificial Analysis
Grok 4.3 (medium)0.299814643188137Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
MiniMax-M2.70.29610750695088Not recordedNot recorded2026-03-18 · model_announcementArtificial Analysis
A.X-K20.295644114921223Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Gemini 3 Pro Preview (low)0.294717330861909Not recordedNot recorded2025-11-18 · model_announcementArtificial Analysis
GLM-5 (Reasoning)0.292863762743281Not recordedNot recorded2026-02-11 · model_announcementArtificial Analysis
Solar Pro 40.292400370713624Not recordedNot recorded2026-08-06 · model_announcementArtificial Analysis
GPT-5.6 Terra (low)0.291936978683967Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Qwen3.5 397B A17B (Reasoning)0.289620018535681Not recordedNot recorded2026-02-16 · model_announcementArtificial Analysis
DeepSeek V3.2 Speciale0.287303058387396Not recordedNot recorded2025-12-01 · model_announcementArtificial Analysis
Solar Open2 250B0.285449490268767Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5 (high)0.28498609823911Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
GPT-5.1 (high)0.28498609823911Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
Nemotron 3 Ultra 550B A55B (Reasoning)0.284059314179796Not recordedNot recorded2026-06-04 · model_announcementArtificial Analysis
GPT-5.4 nano (xhigh)0.282669138090825Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
GPT-5.4 mini (xhigh)0.281278962001854Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
Qwen3 Max Thinking0.279888785912882Not recordedNot recorded2026-01-26 · model_announcementArtificial Analysis
Grok 4.20 0309 v2 (Non-reasoning)0.279425393883225Not recordedNot recorded2026-04-07 · model_announcementArtificial Analysis
GLM-5.1 (Non-reasoning)0.279425393883225Not recordedNot recorded2026-04-07 · model_announcementArtificial Analysis
GPT-5 Codex (high)0.278498609823911Not recordedNot recorded2025-09-23 · model_announcementArtificial Analysis
Qwen3.6 Plus0.278498609823911Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
GLM-5-Turbo0.277571825764597Not recordedNot recorded2026-03-15 · model_announcementArtificial Analysis
Hy3-preview (Reasoning)0.277571825764597Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.6 (low)0.276181649675626Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GLM-4.7 (Reasoning)0.27386468952734Not recordedNot recorded2025-12-22 · model_announcementArtificial Analysis
MiMo-V2.50.272011121408712Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
Grok 40.266913809082484Not recordedNot recorded2025-07-10 · model_announcementArtificial Analysis
GPT-5.2 (medium)0.266913809082484Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
GPT-5.6 Luna (medium)0.257645968489342Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.1 Codex (high)0.257182576459685Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
GPT-5 (medium)0.253938832252085Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Qwen3.5 122B A10B (Reasoning)0.252085264133457Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
Kimi K3 (low)0.249768303985171Not recordedNot recorded2026-07-16 · model_announcementArtificial Analysis
DeepSeek V3.2 (Reasoning)0.245597775718258Not recordedNot recorded2025-12-01 · model_announcementArtificial Analysis
Grok 4.20 0309 (Non-reasoning)0.245134383688601Not recordedNot recorded2026-03-10 · model_announcementArtificial Analysis
Step 3.5 Flash 26030.244670991658943Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Gemini 3.5 Flash (minimal)0.240963855421687Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
Qwen3.5 27B (Reasoning)0.239110287303058Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
Kimi K2 Thinking0.238183503243744Not recordedNot recorded2025-11-06 · model_announcementArtificial Analysis
Ling 3.0 Flash0.236793327154773Not recordedNot recorded2026-08-04 · model_announcementArtificial Analysis
Gemma 4 31B (Reasoning)0.236329935125116Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
MiniMax-M2.10.231696014828545Not recordedNot recorded2025-12-23 · model_announcementArtificial Analysis
Qwen3.6 27B (Reasoning)0.230769230769231Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
MiMo-V2-Flash (Reasoning)0.228452270620945Not recordedNot recorded2025-12-16 · model_announcementArtificial Analysis
MiMo-V2-Omni-03270.225671918443003Not recordedNot recorded2026-03-27 · model_announcementArtificial Analysis
Gemini 2.5 Pro0.225208526413346Not recordedNot recorded2025-06-05 · model_announcementArtificial Analysis
Qwen3.6 35B A3B (Reasoning)0.222428174235403Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
MiMo-V2-Flash (Feb 2026)0.221037998146432Not recordedNot recorded2025-12-16 · model_announcementArtificial Analysis
MiMo-V2-Omni0.221037998146432Not recordedNot recorded2026-03-19 · model_announcementArtificial Analysis
Muse Glimmer (high)0.219647822057461Not recordedNot recorded2026-08-10 · model_announcementArtificial Analysis
GPT-5.5 Instant (May 2026)0.215940685820204Not recordedNot recorded2026-05-05 · model_announcementArtificial Analysis
Ring-2.6-1T0.215940685820204Not recordedNot recorded2026-05-08 · model_announcementArtificial Analysis
GPT-5 mini (high)0.214550509731233Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Step 3.7 Flash0.214087117701576Not recordedNot recorded2026-05-29 · model_announcementArtificial Analysis
Step 3.5 Flash0.211306765523633Not recordedNot recorded2026-02-02 · model_announcementArtificial Analysis
Qwen3.5 35B A3B (Reasoning)0.210379981464319Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
Nemotron 3 Super 120B A12B (Reasoning)0.207599629286376Not recordedNot recorded2026-03-11 · model_announcementArtificial Analysis
MiniMax-M2.50.205282669138091Not recordedNot recorded2026-02-12 · model_announcementArtificial Analysis
o30.2005Not recordedNot recorded2025-04-16 · model_announcementArtificial Analysis
Gemini 2.5 Pro Preview (May' 25)0.1993Not recordedNot recorded2025-05-06 · model_announcementArtificial Analysis
GPT-5.5 Instant (June 2026)0.199258572752549Not recordedNot recorded2026-06-25 · model_announcementArtificial Analysis
GPT-5.6 Luna (low)0.198331788693234Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Qwen3.5 397B A17B (Non-reasoning)0.198331788693234Not recordedNot recorded2026-02-16 · model_announcementArtificial Analysis
gpt-oss-120b (high)0.196014828544949Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Kimi K2.6 (Non-reasoning)0.195551436515292Not recordedNot recorded2026-04-20 · model_announcementArtificial Analysis
GPT-5 (low)0.195551436515292Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Grok 4.1 Fast (Reasoning)0.193234476367006Not recordedNot recorded2025-11-19 · model_announcementArtificial Analysis
Gemma 4 26B A4B (Reasoning)0.193234476367006Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Claude Opus 4.6 (Non-reasoning, High Effort)0.190917516218721Not recordedNot recorded2026-02-05 · model_announcementArtificial Analysis
Grok 4 Fast (Reasoning)0.190917516218721Not recordedNot recorded2025-09-19 · model_announcementArtificial Analysis
Claude Sonnet 5 (Non-reasoning, High Effort)0.190454124189064Not recordedNot recorded2026-06-30 · model_announcementArtificial Analysis
Gemini 3.5 Flash-Lite0.188137164040778Not recordedNot recorded2026-07-21 · model_announcementArtificial Analysis
K-EXAONE 2.0 08030.185820203892493Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.4 mini (medium)0.185820203892493Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
GPT-5.1 Codex mini (high)0.184893419833179Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
Grok 4.3 (low)0.183503243744208Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
Gemini 2.5 Pro Preview (Mar' 25)0.180259499536608Not recordedNot recorded2025-03-25 · model_announcementArtificial Analysis
JT-4.1 Flash 236B A21B0.177942539388323Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude 4.5 Sonnet (Reasoning)0.177942539388323Not recordedNot recorded2025-09-29 · model_announcementArtificial Analysis
G9v3-39A5B0.174698795180723Not recordedNot recorded2026-08-20 · model_announcementArtificial Analysis
Gemini 3.1 Flash-Lite0.17191844300278Not recordedNot recorded2026-03-03 · model_announcementArtificial Analysis
Mercury 20.171455050973123Not recordedNot recorded2026-02-20 · model_announcementArtificial Analysis
GLM 5V Turbo (Reasoning)0.171455050973123Not recordedNot recorded2026-04-01 · model_announcementArtificial Analysis
GPT-5.6 Sol (Non-reasoning)0.166821130676552Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
HyperNova 60B 26050.166357738646895Not recordedNot recorded2026-05-26 · model_announcementArtificial Analysis
o4-mini (high)0.165430954587581Not recordedNot recorded2025-04-16 · model_announcementArtificial Analysis
DeepSeek V3.1 Terminus (Reasoning)0.163577386468953Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
KAT Coder Pro V20.161260426320667Not recordedNot recorded2026-03-27 · model_announcementArtificial Analysis
Qwen3.5 122B A10B (Non-reasoning)0.159406858202039Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
GPT-5.4 nano (medium)0.159406858202039Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
GPT-5 mini (medium)0.159406858202039Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Qwen3 235B A22B 2507 (Reasoning)0.158943466172382Not recordedNot recorded2025-07-25 · model_announcementArtificial Analysis
DeepSeek R1 0528 (May '25)0.158480074142725Not recordedNot recorded2025-05-28 · model_announcementArtificial Analysis
Trinity Large Thinking0.158480074142725Not recordedNot recorded2026-04-01 · model_announcementArtificial Analysis
Gemma 4 12B (Reasoning)0.156626506024096Not recordedNot recorded2026-06-03 · model_announcementArtificial Analysis
Qwen3.6 27B (Non-reasoning)0.150602409638554Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
Gemini 3 Flash Preview (Non-reasoning)0.14967562557924Not recordedNot recorded2025-12-17 · model_announcementArtificial Analysis
Qwen3.5 9B (Reasoning)0.149212233549583Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Qwen3.5 Omni Plus0.148748841519926Not recordedNot recorded2026-03-30 · model_announcementArtificial Analysis
DeepSeek V3.2 Exp (Reasoning)0.148748841519926Not recordedNot recorded2025-09-29 · model_announcementArtificial Analysis
MiMo-V2.5-Pro (Non-reasoning)0.147822057460612Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
GLM-4.6 (Reasoning)0.144578313253012Not recordedNot recorded2025-09-30 · model_announcementArtificial Analysis
DeepSeek V3.1 (Reasoning)0.142724745134384Not recordedNot recorded2025-08-21 · model_announcementArtificial Analysis
Doubao Seed Code0.140871177015755Not recordedNot recorded2025-11-11 · model_announcementArtificial Analysis
Qwen3.8 27B (medium)0.140871177015755Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Qwen3.8 27B (low)0.140407784986098Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Qwen3.5 27B (Non-reasoning)0.139481000926784Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
K-EXAONE (Reasoning)0.139481000926784Not recordedNot recorded2025-12-31 · model_announcementArtificial Analysis
Qwen3.6 35B A3B (Non-reasoning)0.139017608897127Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)0.138090824837813Not recordedNot recorded2025-09-25 · model_announcementArtificial Analysis
Mistral Medium 3.50.137627432808156Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
GPT-5.5 (Non-reasoning)0.137164040778499Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
MiniMax-M20.136700648748842Not recordedNot recorded2025-10-26 · model_announcementArtificial Analysis
Qwen3.5 35B A3B (Non-reasoning)0.134383688600556Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Non-reasoning, High Effort)0.133456904541242Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
ERNIE 5.0 Thinking Preview0.132530120481928Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
Claude Opus 4.5 (Non-reasoning)0.131603336422614Not recordedNot recorded2025-11-24 · model_announcementArtificial Analysis
Kimi K2.5 (Non-reasoning)0.131603336422614Not recordedNot recorded2026-01-27 · model_announcementArtificial Analysis
INTELLECT-30.130676552363299Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
GLM-4.5 (Reasoning)0.129749768303985Not recordedNot recorded2025-07-28 · model_announcementArtificial Analysis
EXAONE 4.5 33B0.128822984244671Not recordedNot recorded2026-04-09 · model_announcementArtificial Analysis
Qwen3 Max Thinking (Preview)0.126506024096386Not recordedNot recorded2025-11-03 · model_announcementArtificial Analysis
Qwen3 Next 80B A3B (Reasoning)0.125579240037071Not recordedNot recorded2025-09-11 · model_announcementArtificial Analysis
Claude 4.1 Opus (Reasoning)0.124652455977757Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Claude 4 Opus (Reasoning)0.123262279888786Not recordedNot recorded2025-05-22 · model_announcementArtificial Analysis
Gemini 2.5 Flash (Reasoning)0.121408711770158Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
Qwen3.8 27B (Non-reasoning)0.121408711770158Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Apriel-v1.5-15B-Thinker0.121408711770158Not recordedNot recorded2025-09-30 · model_announcementArtificial Analysis
Gemini 2.5 Flash Preview (Reasoning)0.121Not recordedNot recorded2025-04-17 · model_announcementArtificial Analysis
o3-mini (high)0.1204Not recordedNot recorded2025-01-31 · model_announcementArtificial Analysis
Nemotron Cascade 2 30B A3B0.120018535681186Not recordedNot recorded2026-03-19 · model_announcementArtificial Analysis
Cogito v2.1 (Reasoning)0.120018535681186Not recordedNot recorded2025-11-18 · model_announcementArtificial Analysis
Command A+0.119555143651529Not recordedNot recorded2026-05-20 · model_announcementArtificial Analysis
Qwen3 Max0.119091751621872Not recordedNot recorded2025-09-23 · model_announcementArtificial Analysis
Qwen3 VL 235B A22B (Reasoning)0.119091751621872Not recordedNot recorded2025-09-23 · model_announcementArtificial Analysis
Gemma 4 31B (Non-reasoning)0.118164967562558Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Nova 2.0 Lite (high)0.11631139944393Not recordedNot recorded2025-10-29 · model_announcementArtificial Analysis
Gemma 4 26B A4B (Non-reasoning)0.114921223354958Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
EXAONE 4.0 32B (Reasoning)0.114457831325301Not recordedNot recorded2025-07-15 · model_announcementArtificial Analysis
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)0.113994439295644Not recordedNot recorded2025-12-15 · model_announcementArtificial Analysis
GPT-5.6 Terra (Non-reasoning)0.113994439295644Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.4 (Non-reasoning)0.112604263206673Not recordedNot recorded2026-03-05 · model_announcementArtificial Analysis
DeepSeek V3.2 (Non-reasoning)0.112140871177016Not recordedNot recorded2025-12-01 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Non-reasoning, Low Effort)0.112140871177016Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
Qwen3 235B A22B 2507 Instruct0.111214087117702Not recordedNot recorded2025-07-21 · model_announcementArtificial Analysis
Ring-1T0.111214087117702Not recordedNot recorded2025-10-13 · model_announcementArtificial Analysis
North Mini Code0.110750695088044Not recordedNot recorded2026-06-09 · model_announcementArtificial Analysis
Sarvam 105B (high)0.110287303058387Not recordedNot recorded2026-03-06 · model_announcementArtificial Analysis
Grok 3 mini Reasoning (high)0.1101Not recordedNot recorded2025-02-19 · model_announcementArtificial Analysis
gpt-oss-20b (high)0.10982391102873Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Falcon-H1R-7B0.10982391102873Not recordedNot recorded2026-01-04 · model_announcementArtificial Analysis
Qwen3 235B A22B (Reasoning)0.1098Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Nanbeige4.1-3B0.108897126969416Not recordedNot recorded2026-02-11 · model_announcementArtificial Analysis
Hermes 4 - Llama-3.1 405B (Reasoning)0.108897126969416Not recordedNot recorded2025-08-27 · model_announcementArtificial Analysis
Step3 VL 10B0.108433734939759Not recordedNot recorded2026-01-20 · model_announcementArtificial Analysis
DiffusionGemma 26B A4B0.108433734939759Not recordedNot recorded2026-06-10 · model_announcementArtificial Analysis
Apriel-v1.6-15B-Thinker0.107970342910102Not recordedNot recorded2025-11-25 · model_announcementArtificial Analysis
Claude 4 Sonnet (Reasoning)0.107043558850788Not recordedNot recorded2025-05-22 · model_announcementArtificial Analysis
Nemotron 3.5 Lightning0.105653382761817Not recordedNot recorded2026-08-11 · model_announcementArtificial Analysis
K2-V2 (high)0.105189990732159Not recordedNot recorded2025-12-05 · model_announcementArtificial Analysis
Solar Open 100B (Reasoning)0.104263206672845Not recordedNot recorded2025-12-17 · model_announcementArtificial Analysis
Claude 4.5 Haiku (Reasoning)0.103799814643188Not recordedNot recorded2025-10-15 · model_announcementArtificial Analysis
Qwen3 30B A3B 2507 (Reasoning)0.102873030583874Not recordedNot recorded2025-07-30 · model_announcementArtificial Analysis
Magistral Medium 1.20.102873030583874Not recordedNot recorded2025-09-18 · model_announcementArtificial Analysis
Solar Pro 30.102873030583874Not recordedNot recorded2026-04-06 · model_announcementArtificial Analysis
Qwen3 Max (Preview)0.101482854494903Not recordedNot recorded2025-09-05 · model_announcementArtificial Analysis
Qwen3 VL 32B (Reasoning)0.101482854494903Not recordedNot recorded2025-10-21 · model_announcementArtificial Analysis
Qwen3 Coder Next0.101482854494903Not recordedNot recorded2026-02-03 · model_announcementArtificial Analysis
K2 Think V20.101019462465246Not recordedNot recorded2025-12-15 · model_announcementArtificial Analysis
Qwen3.5 4B (Reasoning)0.0991658943466172Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Mistral Small 4 (Reasoning)0.0987025023169602Not recordedNot recorded2026-03-16 · model_announcementArtificial Analysis
Seed-OSS-36B-Instruct0.0987025023169602Not recordedNot recorded2025-08-20 · model_announcementArtificial Analysis
Magistral Medium 10.0982391102873031Not recordedNot recorded2025-06-10 · model_announcementArtificial Analysis
GLM-5.2 (Non-reasoning)0.097775718257646Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
Claude 3.7 Sonnet (Reasoning)0.0967Not recordedNot recorded2025-02-24 · model_announcementArtificial Analysis
Ring-flash-2.00.0963855421686747Not recordedNot recorded2025-09-19 · model_announcementArtificial Analysis
GLM-4.6V (Reasoning)0.0963855421686747Not recordedNot recorded2025-12-08 · model_announcementArtificial Analysis
GPT-5 nano (high)0.0949953660797034Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (medium)0.0940685820203892Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
Qwen3.5 9B (Non-reasoning)0.0936051899907322Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Ling 3.0 Tiny0.0931417979610751Not recordedNot recorded2026-08-06 · model_announcementArtificial Analysis
Mi:dm K 2.5 Pro Preview0.0908248378127896Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
DeepSeek V3.2 Exp (Non-reasoning)0.0903614457831325Not recordedNot recorded2025-09-29 · model_announcementArtificial Analysis
Nova 2.0 Lite (medium)0.0898980537534754Not recordedNot recorded2025-10-29 · model_announcementArtificial Analysis
Qwen3 VL 30B A3B (Reasoning)0.0894346617238184Not recordedNot recorded2025-10-03 · model_announcementArtificial Analysis
MiniMax M1 80k0.0889712696941613Not recordedNot recorded2025-06-17 · model_announcementArtificial Analysis
Motif-2-12.7B-Reasoning0.08758109360519Not recordedNot recorded2025-12-04 · model_announcementArtificial Analysis
Hermes 4 - Llama-3.1 70B (Reasoning)0.08758109360519Not recordedNot recorded2025-08-27 · model_announcementArtificial Analysis
Ling-2.6-1T0.0871177015755329Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)0.0871177015755329Not recordedNot recorded2025-09-25 · model_announcementArtificial Analysis
GPT-5 nano (medium)0.0871177015755329Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
DeepSeek V3.1 Terminus (Non-reasoning)0.0866543095458758Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
MiMo-V2-Flash (Non-reasoning)0.0857275254865616Not recordedNot recorded2025-12-16 · model_announcementArtificial Analysis
DeepSeek R1 (Jan '25)0.085Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Non-reasoning)0.082483781278962Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Mi:dm K 2.5 Pro0.0806302131603336Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
GPT-5.2 (Non-reasoning)0.0801668211306766Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
Grok Code Fast 10.0801668211306766Not recordedNot recorded2025-08-28 · model_announcementArtificial Analysis
Qwen3.5 4B (Non-reasoning)0.0797034291010195Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
o3-mini0.0791Not recordedNot recorded2025-01-31 · model_announcementArtificial Analysis
MiniMax M1 40k0.0783132530120482Not recordedNot recorded2025-06-17 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Non-reasoning)0.0778498609823911Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Qwen3 Next 80B A3B Instruct0.0764596848934198Not recordedNot recorded2025-09-11 · model_announcementArtificial Analysis
GLM-5 (Non-reasoning)0.0764596848934198Not recordedNot recorded2026-02-11 · model_announcementArtificial Analysis
GLM-4.7-Flash (Reasoning)0.0759962928637627Not recordedNot recorded2026-01-19 · model_announcementArtificial Analysis
Qwen3.5 Omni Flash0.0759962928637627Not recordedNot recorded2026-03-30 · model_announcementArtificial Analysis
Magistral Small 10.0755329008341057Not recordedNot recorded2025-06-10 · model_announcementArtificial Analysis
Sarvam 30B (high)0.0750695088044486Not recordedNot recorded2026-03-06 · model_announcementArtificial Analysis
Qwen3 Omni 30B A3B (Reasoning)0.0746061167747915Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
Kimi K20.0741427247451344Not recordedNot recorded2025-07-11 · model_announcementArtificial Analysis
Qwen3 32B (Reasoning)0.0741Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)0.0738Not recordedNot recorded2025-04-07 · model_announcementArtificial Analysis
Solar Pro 2 (Reasoning)0.0736793327154773Not recordedNot recorded2025-07-09 · model_announcementArtificial Analysis
QwQ 32B0.0735Not recordedNot recorded2025-03-05 · model_announcementArtificial Analysis
Ling-1T0.0732159406858202Not recordedNot recorded2025-10-08 · model_announcementArtificial Analysis
Llama Nemotron Super 49B v1.5 (Reasoning)0.0732159406858202Not recordedNot recorded2025-07-25 · model_announcementArtificial Analysis
Claude 4.5 Sonnet (Non-reasoning)0.072289156626506Not recordedNot recorded2025-09-29 · model_announcementArtificial Analysis
GPT-5.6 Luna (Non-reasoning)0.072289156626506Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GLM-4.5-Air0.0704355885078777Not recordedNot recorded2025-07-28 · model_announcementArtificial Analysis
o10.0701Not recordedNot recorded2024-12-05 · model_announcementArtificial Analysis
Nova 2.0 Omni (medium)0.0695088044485635Not recordedNot recorded2025-11-26 · model_announcementArtificial Analysis
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)0.0695088044485635Not recordedNot recorded2025-09-08 · model_announcementArtificial Analysis
Hy3-preview (Non-reasoning)0.0695088044485635Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Qwen3 30B A3B 2507 Instruct0.0690454124189064Not recordedNot recorded2025-07-29 · model_announcementArtificial Analysis
LFM2.5-8B-A1B0.0685820203892493Not recordedNot recorded2026-05-28 · model_announcementArtificial Analysis
Qwen3 VL 32B Instruct0.0681186283595922Not recordedNot recorded2025-10-21 · model_announcementArtificial Analysis
Celeris-10.0681186283595922Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Gemini 2.5 Flash-Lite (Reasoning)0.0681186283595922Not recordedNot recorded2025-06-17 · model_announcementArtificial Analysis
Grok 4.3 (Non-reasoning)0.0676552363299351Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
LFM2.5-1.2B-Instruct0.067191844300278Not recordedNot recorded2026-01-05 · model_announcementArtificial Analysis
DeepSeek V3.1 (Non-reasoning)0.0667284522706209Not recordedNot recorded2025-08-21 · model_announcementArtificial Analysis
Qwen3 VL 235B A22B Instruct0.0662650602409639Not recordedNot recorded2025-09-23 · model_announcementArtificial Analysis
GPT-5 (ChatGPT)0.0662650602409639Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Sonar Pro0.0655Not recordedNot recorded2025-01-21 · model_announcementArtificial Analysis
MiniCPM5-1B (Reasoning)0.0648748841519926Not recordedNot recorded2026-05-25 · model_announcementArtificial Analysis
JT-35B-Flash0.0644114921223355Not recordedNot recorded2026-05-14 · model_announcementArtificial Analysis
JT-MINI0.0644114921223355Not recordedNot recorded2026-04-15 · model_announcementArtificial Analysis
Magistral Small 1.20.0644114921223355Not recordedNot recorded2025-09-17 · model_announcementArtificial Analysis
Granite 4.0 H 350M0.0644114921223355Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
Olmo 3 32B Think0.0644114921223355Not recordedNot recorded2025-11-20 · model_announcementArtificial Analysis
Kimi K2 09050.0639481000926784Not recordedNot recorded2025-09-05 · model_announcementArtificial Analysis
GLM-4.7 (Non-reasoning)0.0639481000926784Not recordedNot recorded2025-12-22 · model_announcementArtificial Analysis
Gemini 2.0 Flash Thinking Experimental (Jan '25)0.0635Not recordedNot recorded2025-01-21 · model_announcementArtificial Analysis
Gemma 4 12B (Non-reasoning)0.0634847080630213Not recordedNot recorded2026-06-03 · model_announcementArtificial Analysis
GLM-4.5V (Reasoning)0.0630213160333642Not recordedNot recorded2025-08-11 · model_announcementArtificial Analysis
Qwen3 VL 30B A3B Instruct0.0630213160333642Not recordedNot recorded2025-10-03 · model_announcementArtificial Analysis
Olmo 3.1 32B Think0.0625579240037071Not recordedNot recorded2025-12-12 · model_announcementArtificial Analysis
Ling 2.6 Flash0.0625579240037071Not recordedNot recorded2026-04-21 · model_announcementArtificial Analysis
LFM2.5-1.2B-Thinking0.06209453197405Not recordedNot recorded2026-01-20 · model_announcementArtificial Analysis
Ling-flash-2.00.06209453197405Not recordedNot recorded2025-09-17 · model_announcementArtificial Analysis
LFM2.5-2.6B0.06209453197405Not recordedNot recorded2026-08-04 · model_announcementArtificial Analysis
Gemini 2.0 Pro Experimental (Feb '25)0.0619Not recordedNot recorded2025-02-05 · model_announcementArtificial Analysis
Qwen3 4B 2507 (Reasoning)0.061631139944393Not recordedNot recorded2025-08-06 · model_announcementArtificial Analysis
Claude 4 Opus (Non-reasoning)0.061631139944393Not recordedNot recorded2025-05-22 · model_announcementArtificial Analysis
Qwen3 30B A3B (Reasoning)0.0616Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Solar Pro 2 (Preview) (Reasoning)0.0607043558850788Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
GPT-5 (minimal)0.0602409638554217Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Olmo 3 7B Think0.0597775718257646Not recordedNot recorded2025-11-20 · model_announcementArtificial Analysis
Exaone 4.0 1.2B (Reasoning)0.0597775718257646Not recordedNot recorded2025-07-15 · model_announcementArtificial Analysis
Tri-21B-Think0.0593141797961075Not recordedNot recorded2026-02-10 · model_announcementArtificial Analysis
DeepSeek R1 0528 Qwen3 8B0.0593141797961075Not recordedNot recorded2025-05-29 · model_announcementArtificial Analysis
GPT-5.4 mini (Non-Reasoning)0.0588507877664504Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
gpt-oss-120b (low)0.0588507877664504Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
LongCat Flash Lite0.0583873957367933Not recordedNot recorded2026-01-28 · model_announcementArtificial Analysis
Tri-21B-think Preview0.0579240037071362Not recordedNot recorded2026-02-10 · model_announcementArtificial Analysis
Olmo 3 7B Instruct0.0579240037071362Not recordedNot recorded2025-11-20 · model_announcementArtificial Analysis
Exaone 4.0 1.2B (Non-reasoning)0.0569972196478221Not recordedNot recorded2025-07-15 · model_announcementArtificial Analysis
K-EXAONE (Non-reasoning)0.0569972196478221Not recordedNot recorded2025-12-31 · model_announcementArtificial Analysis
Qwen3 0.6B (Reasoning)0.0564Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3.3 Nemotron Super 49B v1 (Reasoning)0.0562Not recordedNot recorded2025-03-18 · model_announcementArtificial Analysis
LFM2 1.2B0.0556070435588508Not recordedNot recorded2025-07-10 · model_announcementArtificial Analysis
Llama 3.2 Instruct 11B (Vision)0.0553Not recordedNot recorded2024-09-25 · model_announcementArtificial Analysis
Granite 4.0 350M0.0551436515291937Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)0.0551436515291937Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
HyperCLOVA X SEED Think (32B)0.0546802594995366Not recordedNot recorded2025-12-26 · model_announcementArtificial Analysis
Apertus 70B Instruct0.0546802594995366Not recordedNot recorded2025-09-02 · model_announcementArtificial Analysis
LFM2 2.6B0.0546802594995366Not recordedNot recorded2025-09-23 · model_announcementArtificial Analysis
GLM-4.6 (Non-reasoning)0.0546802594995366Not recordedNot recorded2025-09-30 · model_announcementArtificial Analysis
Llama 3.2 Instruct 1B0.0546Not recordedNot recorded2024-09-25 · model_announcementArtificial Analysis
Ministral 3 3B0.0537534754402224Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
OLMo 2 7B0.0537534754402224Not recordedNot recorded2024-11-26 · model_announcementArtificial Analysis
DeepSeek Coder V2 Lite Instruct0.0536Not recordedNot recorded2024-06-17 · model_announcementArtificial Analysis
Llama 3.2 Instruct 3B0.0535Not recordedNot recorded2024-09-25 · model_announcementArtificial Analysis
Llama 2 Chat 7B0.0533Not recordedNot recorded2023-07-18 · model_announcementArtificial Analysis
Gemma 3 1B Instruct0.0532900834105653Not recordedNot recorded2025-03-13 · model_announcementArtificial Analysis
Qwen3 1.7B (Non-reasoning)0.0532Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Gemma 3 4B Instruct0.0529Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
Llama 3.1 Instruct 8B0.0529Not recordedNot recorded2024-07-23 · model_announcementArtificial Analysis
gpt-oss-20b (low)0.0528266913809083Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
GPT-5.1 (Non-reasoning)0.0528266913809083Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
Tiny Aya Global0.0523632993512512Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
Llama 2 Chat 70B0.0521Not recordedNot recorded2023-07-18 · model_announcementArtificial Analysis
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)0.0518999073215941Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (low)0.0518999073215941Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
Molmo 7B-D0.051436515291937Not recordedNot recorded2024-09-25 · model_announcementArtificial Analysis
Jamba 1.5 Mini0.0514Not recordedNot recorded2024-08-22 · model_announcementArtificial Analysis
DeepSeek R1 Distill Llama 70B0.0513Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
LFM2.5-VL-1.6B0.0509731232622799Not recordedNot recorded2026-01-05 · model_announcementArtificial Analysis
Qwen3.5 0.8B (Non-reasoning)0.0509731232622799Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Grok 4.1 Fast (Non-reasoning)0.0509731232622799Not recordedNot recorded2025-11-19 · model_announcementArtificial Analysis
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)0.0509731232622799Not recordedNot recorded2025-09-25 · model_announcementArtificial Analysis
Llama 3 Instruct 8B0.0506Not recordedNot recorded2024-04-18 · model_announcementArtificial Analysis
Ling-mini-2.00.0505097312326228Not recordedNot recorded2025-09-09 · model_announcementArtificial Analysis
MiniCPM-V 4.6 1.3B0.0505097312326228Not recordedNot recorded2026-05-11 · model_announcementArtificial Analysis
GPT-5 mini (minimal)0.0505097312326228Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
GPT-4.1 mini0.0502Not recordedNot recorded2025-04-14 · model_announcementArtificial Analysis
Granite 4.0 Micro0.0500463392029657Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
EXAONE 4.0 32B (Non-reasoning)0.0500463392029657Not recordedNot recorded2025-07-15 · model_announcementArtificial Analysis
Olmo 3.1 32B Instruct0.0500463392029657Not recordedNot recorded2026-01-13 · model_announcementArtificial Analysis
Granite 4.0 H 1B0.0500463392029657Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
Phi-4 Multimodal Instruct0.05Not recordedNot recorded2025-02-26 · model_announcementArtificial Analysis
Phi-3 Mini Instruct 3.8B0.0496Not recordedNot recorded2024-04-23 · model_announcementArtificial Analysis
Qwen3.5 2B (Non-reasoning)0.0495829471733086Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Apertus 8B Instruct0.0495829471733086Not recordedNot recorded2025-09-02 · model_announcementArtificial Analysis
GLM-4.7-Flash (Non-reasoning)0.0495829471733086Not recordedNot recorded2026-01-19 · model_announcementArtificial Analysis
Qwen3 0.6B (Non-reasoning)0.0493Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
LFM 40B0.0493Not recordedNot recorded2024-09-30 · model_announcementArtificial Analysis
LFM2 8B A1B0.0491195551436515Not recordedNot recorded2025-10-07 · model_announcementArtificial Analysis
Llama 4 Maverick0.0491195551436515Not recordedNot recorded2025-04-05 · model_announcementArtificial Analysis
Qwen2.5 Coder Instruct 7B0.0489Not recordedNot recorded2024-09-19 · model_announcementArtificial Analysis
Sonar0.0488Not recordedNot recorded2025-01-21 · model_announcementArtificial Analysis
NVIDIA Nemotron 3 Nano 4B0.0486561631139944Not recordedNot recorded2026-03-16 · model_announcementArtificial Analysis
NVIDIA Nemotron Nano 9B V2 (Reasoning)0.0486561631139944Not recordedNot recorded2025-08-18 · model_announcementArtificial Analysis
Gemma 4 E4B (Non-reasoning)0.0481927710843374Not recordedNot recorded2026-04-03 · model_announcementArtificial Analysis
Nemotron 3 Nano Omni 30B A3B Reasoning0.0481927710843374Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Granite 4.0 1B0.0481927710843374Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
Gemma 3n E4B Instruct Preview (May '25)0.0481927710843374Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
Command-R (Mar '24)0.0479Not recordedNot recorded2024-03-12 · model_announcementArtificial Analysis
OpenChat 3.5 (1210)0.0479Not recordedNot recorded2023-12-18 · model_announcementArtificial Analysis
Gemma 4 E2B (Reasoning)0.0477293790546803Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Llama 2 Chat 13B0.0477Not recordedNot recorded2023-07-18 · model_announcementArtificial Analysis
DeepSeek V3 03240.0474Not recordedNot recorded2025-03-25 · model_announcementArtificial Analysis
Gemini 2.5 Flash (Non-reasoning)0.0472659870250232Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
Gemma 4 E2B (Non-reasoning)0.0472659870250232Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Gemini 1.5 Flash-8B0.0469Not recordedNot recorded2024-10-03 · model_announcementArtificial Analysis
Mistral Medium 3.10.0468025949953661Not recordedNot recorded2025-08-12 · model_announcementArtificial Analysis
Mixtral 8x7B Instruct0.0468Not recordedNot recorded2023-12-11 · model_announcementArtificial Analysis
Gemini 1.5 Pro (Sep '24)0.0464Not recordedNot recorded2024-09-24 · model_announcementArtificial Analysis
Qwen3 1.7B (Reasoning)0.0464Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Qwen3 Omni 30B A3B Instruct0.046339202965709Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
Nova Micro0.046339202965709Not recordedNot recorded2024-12-03 · model_announcementArtificial Analysis
Ministral 3 14B0.046339202965709Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
Command-R+ (Apr '24)0.0463Not recordedNot recorded2024-04-04 · model_announcementArtificial Analysis
Qwen3 30B A3B (Non-reasoning)0.046Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)0.0458758109360519Not recordedNot recorded2025-12-15 · model_announcementArtificial Analysis
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)0.0458758109360519Not recordedNot recorded2025-08-18 · model_announcementArtificial Analysis
Qwen3 VL 4B (Reasoning)0.0458758109360519Not recordedNot recorded2025-10-14 · model_announcementArtificial Analysis
DeepSeek R1 Distill Qwen 32B0.0458Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
Mistral 7B Instruct0.0455Not recordedNot recorded2023-09-27 · model_announcementArtificial Analysis
Qwen3 Coder 480B A35B Instruct0.0454124189063948Not recordedNot recorded2025-07-22 · model_announcementArtificial Analysis
Grok 4 Fast (Non-reasoning)0.0454124189063948Not recordedNot recorded2025-09-19 · model_announcementArtificial Analysis
MiniCPM5-1B (Non-reasoning)0.0454124189063948Not recordedNot recorded2026-05-25 · model_announcementArtificial Analysis
Qwen3 14B (Reasoning)0.0453Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3 Instruct 70B0.0452Not recordedNot recorded2024-04-18 · model_announcementArtificial Analysis
G9v3-3B0.0449490268767377Not recordedNot recorded2026-07-23 · model_announcementArtificial Analysis
Gemma 3n E4B Instruct0.0449490268767377Not recordedNot recorded2025-06-26 · model_announcementArtificial Analysis
Qwen3 4B 2507 Instruct0.0449490268767377Not recordedNot recorded2025-08-06 · model_announcementArtificial Analysis
Llama 3.2 Instruct 90B (Vision)0.0449Not recordedNot recorded2024-09-25 · model_announcementArtificial Analysis
Llama 3.1 Instruct 70B0.0447Not recordedNot recorded2024-07-23 · model_announcementArtificial Analysis
Phi-4 Mini Instruct0.0445Not recordedNot recorded2024-02-26 · model_announcementArtificial Analysis
Grok Beta0.0445Not recordedNot recorded2024-08-13 · model_announcementArtificial Analysis
Jamba 1.7 Mini0.0444856348470806Not recordedNot recorded2025-07-07 · model_announcementArtificial Analysis
Reka Flash 30.0444Not recordedNot recorded2025-03-10 · model_announcementArtificial Analysis
Qwen3 4B (Reasoning)0.0442Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Gemma 3 27B Instruct0.044Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
Gemini 1.5 Flash (May '24)0.0436Not recordedNot recorded2024-05-14 · model_announcementArtificial Analysis
K2-V2 (medium)0.0435588507877665Not recordedNot recorded2025-12-05 · model_announcementArtificial Analysis
Jamba 1.6 Mini0.0431Not recordedNot recorded2025-03-06 · model_announcementArtificial Analysis
Mistral Small 3.10.0430954587581094Not recordedNot recorded2025-03-17 · model_announcementArtificial Analysis
Llama Nemotron Super 49B v1.5 (Non-reasoning)0.0430954587581094Not recordedNot recorded2025-07-25 · model_announcementArtificial Analysis
Mistral Small 3.20.0430954587581094Not recordedNot recorded2025-06-20 · model_announcementArtificial Analysis
Mistral Saba0.043Not recordedNot recorded2025-02-17 · model_announcementArtificial Analysis
Nova Lite0.0429Not recordedNot recorded2024-12-03 · model_announcementArtificial Analysis
Molmo2-8B0.0426320667284523Not recordedNot recorded2025-12-11 · model_announcementArtificial Analysis
Ministral 3 8B0.0426320667284523Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)0.0426320667284523Not recordedNot recorded2025-10-28 · model_announcementArtificial Analysis
Claude 4 Sonnet (Non-reasoning)0.0426320667284523Not recordedNot recorded2025-05-22 · model_announcementArtificial Analysis
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)0.0426Not recordedNot recorded2025-02-13 · model_announcementArtificial Analysis
Gemini 2.0 Flash (Feb '25)0.0426Not recordedNot recorded2025-02-05 · model_announcementArtificial Analysis
Mistral Small (Sep '24)0.0425Not recordedNot recorded2024-09-17 · model_announcementArtificial Analysis
Claude 4.5 Haiku (Non-reasoning)0.0421686746987952Not recordedNot recorded2025-10-15 · model_announcementArtificial Analysis
Hermes 4 - Llama-3.1 405B (Non-reasoning)0.0421686746987952Not recordedNot recorded2025-08-27 · model_announcementArtificial Analysis
LFM2 24B A2B0.0421686746987952Not recordedNot recorded2026-02-25 · model_announcementArtificial Analysis
Gemma 3 12B Instruct0.0421Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
GPT-4o mini0.042Not recordedNot recorded2024-07-18 · model_announcementArtificial Analysis
Qwen3 235B A22B (Non-reasoning)0.0419Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3.1 Nemotron Instruct 70B0.0419Not recordedNot recorded2024-10-15 · model_announcementArtificial Analysis
Gemini 1.0 Pro0.0419Not recordedNot recorded2023-12-06 · model_announcementArtificial Analysis
GPT-4.10.0418Not recordedNot recorded2025-04-14 · model_announcementArtificial Analysis
Granite 3.3 8B (Non-reasoning)0.0417052826691381Not recordedNot recorded2025-04-16 · model_announcementArtificial Analysis
Mistral Large 30.0417052826691381Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
Gemma 3n E2B Instruct0.0417052826691381Not recordedNot recorded2025-06-26 · model_announcementArtificial Analysis
Nova Premier0.0417052826691381Not recordedNot recorded2025-04-30 · model_announcementArtificial Analysis
Claude 3.7 Sonnet (Non-reasoning)0.0416Not recordedNot recorded2025-02-24 · model_announcementArtificial Analysis
DeepSeek R1 Distill Qwen 14B0.0413Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
Qwen3 32B (Non-reasoning)0.0413Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Granite 4.1 30B0.041241890639481Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Grok 30.0412Not recordedNot recorded2025-02-19 · model_announcementArtificial Analysis
Qwen2.5 Turbo0.0409Not recordedNot recorded2024-11-18 · model_announcementArtificial Analysis
Mistral Small (Feb '24)0.0409Not recordedNot recorded2024-02-26 · model_announcementArtificial Analysis
Gemini 2.0 Flash-Lite (Preview)0.0409Not recordedNot recorded2025-02-05 · model_announcementArtificial Analysis
Qwen3 14B (Non-reasoning)0.0409Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Claude 3 Haiku0.0407784986098239Not recordedNot recorded2024-03-04 · model_announcementArtificial Analysis
GPT-5.4 nano (Non-Reasoning)0.0407784986098239Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
Jamba 1.5 Large0.0407Not recordedNot recorded2024-08-22 · model_announcementArtificial Analysis
Gemini 2.0 Flash (experimental)0.0407Not recordedNot recorded2024-12-11 · model_announcementArtificial Analysis
Mistral Medium 30.0405Not recordedNot recorded2025-05-07 · model_announcementArtificial Analysis
Command A0.0403151065801668Not recordedNot recorded2025-03-13 · model_announcementArtificial Analysis
Nova 2.0 Lite (low)0.0403151065801668Not recordedNot recorded2025-10-29 · model_announcementArtificial Analysis
Devstral Small (May '25)0.0403151065801668Not recordedNot recorded2025-05-21 · model_announcementArtificial Analysis
Mixtral 8x22B Instruct0.0401Not recordedNot recorded2024-04-17 · model_announcementArtificial Analysis
Qwen2.5 Instruct 32B0.0399Not recordedNot recorded2024-09-19 · model_announcementArtificial Analysis
Hermes 3 - Llama-3.1 70B0.0399Not recordedNot recorded2024-08-15 · model_announcementArtificial Analysis
GPT-5 nano (minimal)0.0398517145505097Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
Llama 3.1 Instruct 405B0.0398Not recordedNot recorded2024-07-23 · model_announcementArtificial Analysis
GPT-4o (March 2025, chatgpt-4o-latest)0.0397Not recordedNot recorded2025-03-27 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (Non-reasoning)0.0393883225208526Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
QwQ 32B-Preview0.0391Not recordedNot recorded2024-11-27 · model_announcementArtificial Analysis
Qwen3 8B (Reasoning)0.0389Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Claude 2.10.0389Not recordedNot recorded2023-11-21 · model_announcementArtificial Analysis
Nova 2.0 Omni (Non-reasoning)0.0384615384615385Not recordedNot recorded2025-11-26 · model_announcementArtificial Analysis
Qwen3 Coder 30B A3B Instruct0.0384615384615385Not recordedNot recorded2025-07-31 · model_announcementArtificial Analysis
Qwen3 VL 8B (Reasoning)0.0384615384615385Not recordedNot recorded2025-10-14 · model_announcementArtificial Analysis
Qwen2.5 Max0.0382Not recordedNot recorded2025-01-28 · model_announcementArtificial Analysis
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)0.0381Not recordedNot recorded2025-03-18 · model_announcementArtificial Analysis
Gemini 2.5 Flash Preview (Non-reasoning)0.038Not recordedNot recorded2025-04-17 · model_announcementArtificial Analysis
Mistral Small 4 (Non-reasoning)0.0379981464318814Not recordedNot recorded2026-03-16 · model_announcementArtificial Analysis
Granite 4.0 H Small0.0379981464318814Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
Granite 4.1 8B0.0379981464318814Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Llama 4 Scout0.0378Not recordedNot recorded2025-04-05 · model_announcementArtificial Analysis
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)0.0376Not recordedNot recorded2025-03-13 · model_announcementArtificial Analysis
Mistral Small 30.0376Not recordedNot recorded2025-01-30 · model_announcementArtificial Analysis
Phi-40.0376Not recordedNot recorded2024-12-12 · model_announcementArtificial Analysis
GPT-4.1 nano0.0375347544022243Not recordedNot recorded2025-04-14 · model_announcementArtificial Analysis
Devstral Small (Jul '25)0.0375347544022243Not recordedNot recorded2025-07-10 · model_announcementArtificial Analysis
Devstral Medium0.0375347544022243Not recordedNot recorded2025-07-10 · model_announcementArtificial Analysis
Gemma 4 E4B (Reasoning)0.0375347544022243Not recordedNot recorded2026-04-03 · model_announcementArtificial Analysis
Jamba Reasoning 3B0.0375347544022243Not recordedNot recorded2025-10-08 · model_announcementArtificial Analysis
Solar Pro 2 (Non-reasoning)0.0370713623725672Not recordedNot recorded2025-07-09 · model_announcementArtificial Analysis
Claude 3.5 Sonnet (Oct '24)0.0369Not recordedNot recorded2024-10-22 · model_announcementArtificial Analysis
Gemini 2.5 Flash-Lite (Non-reasoning)0.0366079703429101Not recordedNot recorded2025-06-17 · model_announcementArtificial Analysis
GLM-4.6V (Non-reasoning)0.0366079703429101Not recordedNot recorded2025-12-08 · model_announcementArtificial Analysis
Solar Pro 2 (Preview) (Non-reasoning)0.0366079703429101Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
Jamba 1.7 Large0.0366079703429101Not recordedNot recorded2025-07-07 · model_announcementArtificial Analysis
Qwen2 Instruct 72B0.0366Not recordedNot recorded2024-06-07 · model_announcementArtificial Analysis
Claude 3.5 Haiku0.0363Not recordedNot recorded2024-10-22 · model_announcementArtificial Analysis
Claude 3 Sonnet0.0362Not recordedNot recorded2024-03-04 · model_announcementArtificial Analysis
Gemma 3 270M0.036144578313253Not recordedNot recorded2025-08-14 · model_announcementArtificial Analysis
OLMo 2 32B0.036144578313253Not recordedNot recorded2025-03-13 · model_announcementArtificial Analysis
K2-V2 (low)0.036144578313253Not recordedNot recorded2025-12-05 · model_announcementArtificial Analysis
Qwen3 VL 4B Instruct0.036144578313253Not recordedNot recorded2025-10-14 · model_announcementArtificial Analysis
Jamba 1.6 Large0.0361Not recordedNot recorded2025-03-06 · model_announcementArtificial Analysis
o1-mini0.0357Not recordedNot recorded2024-09-12 · model_announcementArtificial Analysis
Devstral 20.0356811862835959Not recordedNot recorded2025-12-09 · model_announcementArtificial Analysis
Hermes 4 - Llama-3.1 70B (Non-reasoning)0.0356811862835959Not recordedNot recorded2025-08-27 · model_announcementArtificial Analysis
Llama 3.3 Instruct 70B0.0356Not recordedNot recorded2024-12-06 · model_announcementArtificial Analysis
Qwen2.5 Instruct 72B0.0356Not recordedNot recorded2024-09-19 · model_announcementArtificial Analysis
Claude Instant0.0353Not recordedNot recorded2023-03-14 · model_announcementArtificial Analysis
Qwen2.5 Coder Instruct 32B0.0351Not recordedNot recorded2024-11-11 · model_announcementArtificial Analysis
Mistral Medium0.0351Not recordedNot recorded2023-12-11 · model_announcementArtificial Analysis
Mistral Large (Feb '24)0.035Not recordedNot recorded2024-02-26 · model_announcementArtificial Analysis
Gemini 1.5 Pro (May '24)0.0348Not recordedNot recorded2024-05-15 · model_announcementArtificial Analysis
GLM-4.5V (Non-reasoning)0.0347544022242817Not recordedNot recorded2025-08-11 · model_announcementArtificial Analysis
Devstral Small 20.0347544022242817Not recordedNot recorded2025-12-09 · model_announcementArtificial Analysis
Granite 4.1 3B0.0342910101946247Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Gemini 2.0 Flash-Lite (Feb '25)0.0335Not recordedNot recorded2025-02-25 · model_announcementArtificial Analysis
Mistral Large 2 (Nov '24)0.0334Not recordedNot recorded2024-11-18 · model_announcementArtificial Analysis
ERNIE 4.5 300B A47B0.0333642261353105Not recordedNot recorded2025-06-30 · model_announcementArtificial Analysis
Qwen3 4B (Non-reasoning)0.0332Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3.1 Tulu3 405B0.0328Not recordedNot recorded2025-01-30 · model_announcementArtificial Analysis
Claude 3.5 Sonnet (June '24)0.0323Not recordedNot recorded2024-06-21 · model_announcementArtificial Analysis
Nova Pro0.0319Not recordedNot recorded2024-12-03 · model_announcementArtificial Analysis
Gemini 1.5 Flash (Sep '24)0.0317Not recordedNot recorded2024-09-24 · model_announcementArtificial Analysis
GPT-4 Turbo0.0313Not recordedNot recorded2023-11-06 · model_announcementArtificial Analysis
Sarvam M (Reasoning)0.031047265987025Not recordedNot recorded2025-05-23 · model_announcementArtificial Analysis
DeepSeek R1 Distill Qwen 1.5B0.0308Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
Grok 2 (Dec '24)0.0306Not recordedNot recorded2024-12-12 · model_announcementArtificial Analysis
Mistral Large 2 (Jul '24)0.0295Not recordedNot recorded2024-07-24 · model_announcementArtificial Analysis
DBRX Instruct0.0292Not recordedNot recorded2024-03-27 · model_announcementArtificial Analysis
DeepSeek V3 (Dec '24)0.029Not recordedNot recorded2024-12-26 · model_announcementArtificial Analysis
Nova 2.0 Lite (Non-reasoning)0.0287303058387396Not recordedNot recorded2025-10-29 · model_announcementArtificial Analysis
Pixtral Large0.028Not recordedNot recorded2024-11-18 · model_announcementArtificial Analysis
Claude 3 Opus0.0275Not recordedNot recorded2024-03-04 · model_announcementArtificial Analysis
GPT-4o (ChatGPT)0.0273Not recordedNot recorded2025-02-15 · model_announcementArtificial Analysis
Qwen3 VL 8B Instruct0.0268767377201112Not recordedNot recorded2025-10-14 · model_announcementArtificial Analysis
Qwen3.5 2B (Reasoning)0.025949953660797Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Kimi Linear 48B A3B Instruct0.0245597775718258Not recordedNot recorded2025-10-30 · model_announcementArtificial Analysis
GPT-4o (Nov '24)0.0242Not recordedNot recorded2024-11-20 · model_announcementArtificial Analysis
GPT-4o (Aug '24)0.0233Not recordedNot recorded2024-08-06 · model_announcementArtificial Analysis
Qwen3 8B (Non-reasoning)0.0195Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
GPT-4o (May '24)0.0176Not recordedNot recorded2024-05-13 · model_announcementArtificial Analysis
Qwen3.5 0.8B (Reasoning)0.0106580166821131Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis

Explore related benchmarks

Suggestions based on shared evidence or source categories, not verified equivalents.

AA-Omniscience Non-Hallucination RateShared source categories →AA-Omniscience AccuracyShared source categories →CritPtShared source categories →AA-LCRShared source categories →GPQA DiamondShared source categories →SciCodeShared source categories →τ³-BankingShared source categories →GDPval-AA v2 (Elo)Shared source categories →

Put this benchmark in context

Reasoning and math benchmarks

Continue exploring

Search the catalog using this record’s source labels. Search matches are not verified equivalents.

intelligence-index →reasoning →knowledge →Artificial Analysis · all records →