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

Artificial Analysis

Terminal-Bench v2.1

Agentic coding & terminal use

Evaluation context and evidence

Source
Artificial Analysis
Publisher
Not recorded
Benchmark release
2026-05-06
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.

Original sources

Reported results 210

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

ModelValueUnitProtocolReported date and basisSource
GPT-5.6 Sol (xhigh)0.895131086142322Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Max Effort)0.891385767790262Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Grok 4.6 (high)0.883895131086142Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)0.880149812734082Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
GPT-5.6 Terra (max)0.880149812734082Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok 4.6 (xhigh)0.880149812734082Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.6 Sol (max)0.880149812734082Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, High Effort)0.876404494382023Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
GPT-5.6 Sol (high)0.872659176029963Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Sol (medium)0.861423220973783Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Medium Effort)0.861423220973783Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Gemini 3.7 Flash (high)0.857677902621723Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
Kimi K3 (max)0.850187265917603Not recordedNot recorded2026-07-16 · model_announcementArtificial Analysis
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)0.846441947565543Not recordedNot recorded2026-05-28 · model_announcementArtificial Analysis
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)0.846441947565543Not recordedNot recorded2026-06-09 · model_announcementArtificial Analysis
GPT-5.5 (xhigh)0.842696629213483Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.6 (medium)0.842696629213483Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GLM-5.3 (max)0.838951310861423Not recordedNot recorded2026-08-18 · model_announcementArtificial Analysis
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)0.831460674157303Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
Kimi K3 (low)0.823970037453184Not recordedNot recorded2026-07-16 · model_announcementArtificial Analysis
Qwen3.8 2.4T A95B0.820224719101124Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Grok 4.5 (high)0.816479400749064Not recordedNot recorded2026-07-08 · model_announcementArtificial Analysis
Qwen3.8 Max0.812734082397004Not recordedNot recorded2026-08-03 · model_announcementArtificial Analysis
GPT-5.6 Luna (max)0.808988764044944Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)0.805243445692884Not recordedNot recorded2026-06-30 · model_announcementArtificial Analysis
GPT-5.5 (medium)0.805243445692884Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Muse Spark 1.2 (xhigh)0.801498127340824Not recordedNot recorded2026-08-05 · model_announcementArtificial Analysis
GPT-5.6 Terra (xhigh)0.801498127340824Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Qwen3.8 27B (xhigh)0.797752808988764Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Gemini 3.7 Flash (low)0.797752808988764Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
GPT-5.5 (high)0.794007490636704Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Gemini 3.5 Flash (high)0.786516853932584Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)0.786516853932584Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)0.786516853932584Not recordedNot recorded2026-07-31 · model_announcementArtificial Analysis
GPT-5.4 (xhigh)0.782771535580524Not recordedNot recorded2026-03-05 · model_announcementArtificial Analysis
Gemini 3.7 Flash (medium)0.782771535580524Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
GPT-5.6 Luna (xhigh)0.779026217228464Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Muse Spark 1.1 (xhigh)0.779026217228464Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GLM-5.2 (max)0.779026217228464Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
Gemini 3.6 Flash (high)0.775280898876405Not recordedNot recorded2026-07-21 · model_announcementArtificial Analysis
GPT-5.6 Sol (low)0.767790262172285Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Low Effort)0.764044943820225Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
GPT-5.6 Terra (high)0.756554307116105Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok 4.6 (low)0.752808988764045Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Claude Sonnet 5 (Non-reasoning, High Effort)0.752808988764045Not recordedNot recorded2026-06-30 · model_announcementArtificial Analysis
Motif 30.749063670411985Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Qwen3.7 Max0.745318352059925Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
DeepSeek V4 Flash Vision (Reasoning, Max Effort)0.741573033707865Not recordedNot recorded2026-08-21 · model_announcementArtificial Analysis
GPT-5.6 Sol (Non-reasoning)0.741573033707865Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemini 3.1 Pro Preview0.737827715355805Not recordedNot recorded2026-02-19 · model_announcementArtificial Analysis
GPT-5.6 Terra (medium)0.722846441947566Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)0.711610486891386Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
Motif 3 (Beta)0.707865168539326Not recordedNot recorded2026-07-14 · model_announcementArtificial Analysis
KAT Coder Pro V20.700374531835206Not recordedNot recorded2026-03-27 · model_announcementArtificial Analysis
GPT-5.6 Luna (high)0.696629213483146Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Nex-N2-Pro0.677902621722846Not recordedNot recorded2026-06-02 · model_announcementArtificial Analysis
Qwen3.8 27B (low)0.674157303370786Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Kimi K2.7 Code0.674157303370786Not recordedNot recorded2026-06-12 · model_announcementArtificial Analysis
Agnes 2.5 Pro Alpha0.670411985018727Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Kimi K2.60.659176029962547Not recordedNot recorded2026-04-20 · model_announcementArtificial Analysis
GPT-5.5 (low)0.655430711610487Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
MiMo-V2.5-Pro0.651685393258427Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
MiniMax-M30.651685393258427Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
Qwen3.8 27B (medium)0.651685393258427Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, High Effort)0.647940074906367Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Hy30.644194756554307Not recordedNot recorded2026-07-06 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, Max Effort)0.640449438202247Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
MiMo-V2.50.636704119850187Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
GPT-5.6 Terra (low)0.625468164794007Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Muse Spark0.621722846441948Not recordedNot recorded2026-04-08 · model_announcementArtificial Analysis
GLM-5.1 (Reasoning)0.617977528089888Not recordedNot recorded2026-04-07 · model_announcementArtificial Analysis
MiMo-V2-Flash (Non-reasoning)0.617977528089888Not recordedNot recorded2025-12-16 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, Max Effort)0.617977528089888Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Qwen3.6 Plus0.614232209737828Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
GPT-5.5 (Non-reasoning)0.610486891385768Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Qwen3.7 Plus0.610486891385768Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
Qwen3.6 27B (Reasoning)0.606741573033708Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
GPT-5.4 nano (xhigh)0.606741573033708Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
JT-4.1 Flash 236B A21B0.595505617977528Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.4 mini (xhigh)0.591760299625468Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
Solar Pro 40.573033707865168Not recordedNot recorded2026-08-06 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, High Effort)0.569288389513109Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
GPT-5.6 Terra (Non-reasoning)0.561797752808989Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude 4.5 Sonnet (Reasoning)0.558052434456929Not recordedNot recorded2025-09-29 · model_announcementArtificial Analysis
MiniMax-M2.70.554307116104869Not recordedNot recorded2026-03-18 · model_announcementArtificial Analysis
Ling 3.0 Flash0.554307116104869Not recordedNot recorded2026-08-04 · model_announcementArtificial Analysis
Inkling (xhigh)0.550561797752809Not recordedNot recorded2026-07-15 · model_announcementArtificial Analysis
Inkling Small0.550561797752809Not recordedNot recorded2026-07-30 · model_announcementArtificial Analysis
Nemotron 3 Ultra 550B A55B (Reasoning)0.539325842696629Not recordedNot recorded2026-06-04 · model_announcementArtificial Analysis
Gemini 3.5 Flash-Lite0.535580524344569Not recordedNot recorded2026-07-21 · model_announcementArtificial Analysis
GPT-5.6 Luna (medium)0.531835205992509Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.1 (high)0.524344569288389Not recordedNot recorded2025-11-13 · model_announcementArtificial Analysis
Grok Build 0.1 06160.52059925093633Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
Muse Glimmer (high)0.51685393258427Not recordedNot recorded2026-08-10 · model_announcementArtificial Analysis
GLM-5.2 (Non-reasoning)0.51685393258427Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
Qwen3.5 397B A17B (Reasoning)0.51310861423221Not recordedNot recorded2026-02-16 · model_announcementArtificial Analysis
Qwen3.6 27B (Non-reasoning)0.51310861423221Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
Mistral Medium 3.50.50561797752809Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
LongCat 2.00.50187265917603Not recordedNot recorded2026-06-29 · model_announcementArtificial Analysis
GLM-4.6 (Reasoning)0.49438202247191Not recordedNot recorded2025-09-30 · model_announcementArtificial Analysis
Qwen3.8 27B (Non-reasoning)0.49063670411985Not recordedNot recorded2026-08-14 · model_announcementArtificial Analysis
Qwen3.5 122B A10B (Reasoning)0.47565543071161Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
Qwen3.5 122B A10B (Non-reasoning)0.471910112359551Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
DeepSeek V3.2 (Reasoning)0.468164794007491Not recordedNot recorded2025-12-01 · model_announcementArtificial Analysis
Kimi K2.5 (Reasoning)0.456928838951311Not recordedNot recorded2026-01-27 · model_announcementArtificial Analysis
GLM-4.7 (Reasoning)0.453183520599251Not recordedNot recorded2025-12-22 · model_announcementArtificial Analysis
DeepSeek V3.1 Terminus (Reasoning)0.449438202247191Not recordedNot recorded2025-09-22 · model_announcementArtificial Analysis
Qwen3.6 35B A3B (Reasoning)0.449438202247191Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
Solar Open2 250B0.441947565543071Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Claude 4.5 Haiku (Reasoning)0.441947565543071Not recordedNot recorded2025-10-15 · model_announcementArtificial Analysis
GPT-5.6 Luna (low)0.434456928838951Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemma 4 31B (Reasoning)0.434456928838951Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Ring-2.6-1T0.430711610486891Not recordedNot recorded2026-05-08 · model_announcementArtificial Analysis
Qwen3.6 35B A3B (Non-reasoning)0.415730337078652Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
Qwen3.5 35B A3B (Non-reasoning)0.408239700374532Not recordedNot recorded2026-02-24 · model_announcementArtificial Analysis
K-EXAONE 2.0 08030.404494382022472Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Grok 4.3 (high)0.397003745318352Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
Step 3.7 Flash0.393258426966292Not recordedNot recorded2026-05-29 · model_announcementArtificial Analysis
Gemma 4 26B A4B (Reasoning)0.389513108614232Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
A.X-K20.389513108614232Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
GPT-5.6 Luna (Non-reasoning)0.389513108614232Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Nemotron 3 Super 120B A12B (Reasoning)0.385767790262172Not recordedNot recorded2026-03-11 · model_announcementArtificial Analysis
Qwen3 Coder Next0.382022471910112Not recordedNot recorded2026-02-03 · model_announcementArtificial Analysis
Claude 4 Sonnet (Reasoning)0.363295880149813Not recordedNot recorded2025-05-22 · model_announcementArtificial Analysis
North Mini Code0.355805243445693Not recordedNot recorded2026-06-09 · model_announcementArtificial Analysis
GPT-5 (high)0.352059925093633Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
GPT-5.5 Instant (June 2026)0.348314606741573Not recordedNot recorded2026-06-25 · model_announcementArtificial Analysis
Grok 4.3 (Non-reasoning)0.340823970037453Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
G9v3-39A5B0.325842696629214Not recordedNot recorded2026-08-20 · model_announcementArtificial Analysis
Gemini 3.1 Flash-Lite0.310861423220974Not recordedNot recorded2026-03-03 · model_announcementArtificial Analysis
Devstral 20.303370786516854Not recordedNot recorded2025-12-09 · model_announcementArtificial Analysis
K-EXAONE (Reasoning)0.303370786516854Not recordedNot recorded2025-12-31 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (medium)0.295880149812734Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
Devstral Small 20.295880149812734Not recordedNot recorded2025-12-09 · model_announcementArtificial Analysis
Qwen3.5 9B (Reasoning)0.292134831460674Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Gemma 4 31B (Non-reasoning)0.292134831460674Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Gemini 2.5 Pro0.284644194756554Not recordedNot recorded2025-06-05 · model_announcementArtificial Analysis
Ling 3.0 Tiny0.277153558052434Not recordedNot recorded2026-08-06 · model_announcementArtificial Analysis
Mercury 20.273408239700375Not recordedNot recorded2026-02-20 · model_announcementArtificial Analysis
Gemma 4 12B (Reasoning)0.273408239700375Not recordedNot recorded2026-06-03 · model_announcementArtificial Analysis
Mistral Small 3.10.262172284644195Not recordedNot recorded2025-03-17 · model_announcementArtificial Analysis
gpt-oss-120b (high)0.262172284644195Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Qwen3.5 4B (Reasoning)0.258426966292135Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Nemotron 3.5 Lightning0.243445692883895Not recordedNot recorded2026-08-11 · model_announcementArtificial Analysis
Ling 2.6 Flash0.243445692883895Not recordedNot recorded2026-04-21 · model_announcementArtificial Analysis
Command A+0.228464419475655Not recordedNot recorded2026-05-20 · model_announcementArtificial Analysis
Qwen3.5 9B (Non-reasoning)0.213483146067416Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Qwen3.5 4B (Non-reasoning)0.213483146067416Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
EXAONE 4.5 33B0.213483146067416Not recordedNot recorded2026-04-09 · model_announcementArtificial Analysis
Mistral Small 4 (Reasoning)0.209737827715356Not recordedNot recorded2026-03-16 · model_announcementArtificial Analysis
Nemotron Cascade 2 30B A3B0.205992509363296Not recordedNot recorded2026-03-19 · model_announcementArtificial Analysis
Trinity Large Thinking0.205992509363296Not recordedNot recorded2026-04-01 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (low)0.194756554307116Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
DeepSeek R1 (Jan '25)0.191011235955056Not recordedNot recorded2025-01-20 · model_announcementArtificial Analysis
HyperNova 60B 26050.183520599250936Not recordedNot recorded2026-05-26 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (Non-reasoning)0.172284644194757Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
DeepSeek V3 (Dec '24)0.168539325842697Not recordedNot recorded2024-12-26 · model_announcementArtificial Analysis
Nova 2.0 Lite (high)0.161048689138577Not recordedNot recorded2025-10-29 · model_announcementArtificial Analysis
K2 Think V20.149812734082397Not recordedNot recorded2025-12-15 · model_announcementArtificial Analysis
Mistral Medium 3.10.138576779026217Not recordedNot recorded2025-08-12 · model_announcementArtificial Analysis
gpt-oss-20b (high)0.138576779026217Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
DeepSeek V3 03240.138576779026217Not recordedNot recorded2025-03-25 · model_announcementArtificial Analysis
gpt-oss-120b (low)0.138576779026217Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Magistral Medium 1.20.123595505617978Not recordedNot recorded2025-09-18 · model_announcementArtificial Analysis
DiffusionGemma 26B A4B0.123595505617978Not recordedNot recorded2026-06-10 · model_announcementArtificial Analysis
Mistral Large 30.119850187265918Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
Solar Pro 30.119850187265918Not recordedNot recorded2026-04-06 · model_announcementArtificial Analysis
Qwen3 235B A22B 2507 (Reasoning)0.119850187265918Not recordedNot recorded2025-07-25 · model_announcementArtificial Analysis
Celeris-10.112359550561798Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude 3.5 Haiku0.101123595505618Not recordedNot recorded2024-10-22 · model_announcementArtificial Analysis
GPT-4.1 mini0.101123595505618Not recordedNot recorded2025-04-14 · model_announcementArtificial Analysis
Ministral 3 14B0.0973782771535581Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
Llama 4 Maverick0.0786516853932584Not recordedNot recorded2025-04-05 · model_announcementArtificial Analysis
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)0.0674157303370786Not recordedNot recorded2025-12-15 · model_announcementArtificial Analysis
Nemotron 3 Nano Omni 30B A3B Reasoning0.0674157303370786Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Qwen3 Next 80B A3B (Reasoning)0.0674157303370786Not recordedNot recorded2025-09-11 · model_announcementArtificial Analysis
G9v3-3B0.0599250936329588Not recordedNot recorded2026-07-23 · model_announcementArtificial Analysis
Mistral Small 3.20.0561797752808989Not recordedNot recorded2025-06-20 · model_announcementArtificial Analysis
GPT-4o mini0.0561797752808989Not recordedNot recorded2024-07-18 · model_announcementArtificial Analysis
Qwen3 32B (Reasoning)0.052434456928839Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Qwen3 14B (Reasoning)0.048689138576779Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Llama 3.3 Instruct 70B0.048689138576779Not recordedNot recorded2024-12-06 · model_announcementArtificial Analysis
o3-mini (high)0.0449438202247191Not recordedNot recorded2025-01-31 · model_announcementArtificial Analysis
Gemma 3 27B Instruct0.0449438202247191Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
Magistral Small 1.20.0449438202247191Not recordedNot recorded2025-09-17 · model_announcementArtificial Analysis
LFM2.5-2.6B0.0449438202247191Not recordedNot recorded2026-08-04 · model_announcementArtificial Analysis
Ministral 3 8B0.0411985018726592Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
GPT-5 mini (high)0.0374531835205993Not recordedNot recorded2025-08-07 · model_announcementArtificial Analysis
GPT-4.1 nano0.0374531835205993Not recordedNot recorded2025-04-14 · model_announcementArtificial Analysis
NVIDIA Nemotron 3 Nano 4B0.0374531835205993Not recordedNot recorded2026-03-16 · model_announcementArtificial Analysis
Llama 4 Scout0.0374531835205993Not recordedNot recorded2025-04-05 · model_announcementArtificial Analysis
Granite 4.1 8B0.0337078651685393Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Qwen3.5 2B (Reasoning)0.0299625468164794Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Granite 4.1 30B0.0262172284644195Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Qwen3 8B (Reasoning)0.0224719101123595Not recordedNot recorded2025-04-28 · model_announcementArtificial Analysis
Gemma 4 E4B (Reasoning)0.0187265917602996Not recordedNot recorded2026-04-03 · model_announcementArtificial Analysis
Qwen3 30B A3B 2507 (Reasoning)0.0149812734082397Not recordedNot recorded2025-07-30 · model_announcementArtificial Analysis
Llama 3.1 Instruct 8B0.0149812734082397Not recordedNot recorded2024-07-23 · model_announcementArtificial Analysis
Nanbeige4.1-3B0.0112359550561798Not recordedNot recorded2026-02-11 · model_announcementArtificial Analysis
Granite 4.1 3B0.0112359550561798Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
Gemma 3n E4B Instruct0.00749063670411985Not recordedNot recorded2025-06-26 · model_announcementArtificial Analysis
Gemma 3 4B Instruct0.00374531835205993Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
Qwen3.5 0.8B (Non-reasoning)0.00374531835205993Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Phi-4 Mini Instruct0.00374531835205993Not recordedNot recorded2024-02-26 · model_announcementArtificial Analysis
Gemma 4 E2B (Reasoning)0.00374531835205993Not recordedNot recorded2026-04-02 · model_announcementArtificial Analysis
Qwen3.5 2B (Non-reasoning)0Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis
Gemma 3 12B Instruct0Not recordedNot recorded2025-03-12 · model_announcementArtificial Analysis
MiniCPM-V 4.6 1.3B0Not recordedNot recorded2026-05-11 · model_announcementArtificial Analysis
Ministral 3 3B0Not recordedNot recorded2025-12-02 · model_announcementArtificial Analysis
Qwen3.5 0.8B (Reasoning)0Not recordedNot recorded2026-03-02 · model_announcementArtificial Analysis

Put this benchmark in context

Coding benchmarksTools and agents benchmarks