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

Artificial Analysis

MLCR-AA

MLCR-AA overall score

Evaluation context and evidence

Source
Artificial Analysis
Publisher
Not recorded
Benchmark release
Not recorded
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 71

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)0.644444444444444Not recordedNot recorded2026-06-09 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, High Effort)0.594444444444444Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)0.583333333333333Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Medium Effort)0.561111111111111Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Max Effort)0.555555555555556Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)0.55Not recordedNot recorded2026-06-30 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Low Effort)0.538888888888889Not recordedNot recorded2026-07-24 · model_announcementArtificial Analysis
GLM-5.3 (max)0.483333333333333Not recordedNot recorded2026-08-18 · model_announcementArtificial Analysis
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)0.455555555555556Not recordedNot recorded2026-05-28 · model_announcementArtificial Analysis
Kimi K3 (max)0.383333333333333Not recordedNot recorded2026-07-16 · model_announcementArtificial Analysis
GPT-5.6 Terra (max)0.316666666666667Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Muse Spark 1.2 (xhigh)0.311111111111111Not recordedNot recorded2026-08-05 · model_announcementArtificial Analysis
Claude Opus 4.7 (Non-reasoning, High Effort)0.288888888888889Not recordedNot recorded2026-04-16 · model_announcementArtificial Analysis
GPT-5.6 Sol (max)0.261111111111111Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)0.244444444444444Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
GPT-5.6 Terra (xhigh)0.216666666666667Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, Max Effort)0.211111111111111Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Non-reasoning, Low Effort)0.205555555555556Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Non-reasoning, High Effort)0.2Not recordedNot recorded2026-02-17 · model_announcementArtificial Analysis
GPT-5.6 Luna (max)0.194444444444444Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Qwen3.8 Max0.194444444444444Not recordedNot recorded2026-08-03 · model_announcementArtificial Analysis
Gemini 3.5 Flash (high)0.183333333333333Not recordedNot recorded2026-05-19 · model_announcementArtificial Analysis
GPT-5.6 Sol (xhigh)0.183333333333333Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.5 (xhigh)0.177777777777778Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)0.177777777777778Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
MiniMax-M30.172222222222222Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
GPT-5.6 Sol (high)0.172222222222222Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Luna (xhigh)0.161111111111111Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Kimi K2.7 Code0.161111111111111Not recordedNot recorded2026-06-12 · model_announcementArtificial Analysis
Gemini 3.1 Pro Preview0.155555555555556Not recordedNot recorded2026-02-19 · model_announcementArtificial Analysis
GPT-5.6 Sol (medium)0.15Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.5 (Non-reasoning)0.15Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.5 (high)0.15Not recordedNot recorded2026-07-08 · model_announcementArtificial Analysis
Gemini 3.7 Flash (high)0.15Not recordedNot recorded2026-08-13 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, Max Effort)0.15Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
Gemini 3.6 Flash (high)0.144444444444444Not recordedNot recorded2026-07-21 · model_announcementArtificial Analysis
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)0.133333333333333Not recordedNot recorded2026-07-31 · model_announcementArtificial Analysis
GPT-5.6 Sol (low)0.127777777777778Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Inkling (xhigh)0.122222222222222Not recordedNot recorded2026-07-15 · model_announcementArtificial Analysis
GPT-5.6 Terra (medium)0.122222222222222Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Terra (high)0.122222222222222Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Luna (high)0.122222222222222Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Grok 4.6 (high)0.122222222222222Not recordedNot recorded2026-08-12 · model_announcementArtificial Analysis
Gemini 3 Flash Preview (Non-reasoning)0.116666666666667Not recordedNot recorded2025-12-17 · model_announcementArtificial Analysis
Nemotron 3 Ultra 550B A55B (Reasoning)0.111111111111111Not recordedNot recorded2026-06-04 · model_announcementArtificial Analysis
Gemini 3 Flash Preview (Reasoning)0.111111111111111Not recordedNot recorded2025-12-17 · model_announcementArtificial Analysis
GPT-5.5 (low)0.111111111111111Not recordedNot recorded2026-04-23 · model_announcementArtificial Analysis
Grok 4.3 (high)0.1Not recordedNot recorded2026-04-30 · model_announcementArtificial Analysis
MiMo-V2.5-Pro0.0944444444444444Not recordedNot recorded2026-04-22 · model_announcementArtificial Analysis
Qwen3.7 Plus0.0944444444444444Not recordedNot recorded2026-06-01 · model_announcementArtificial Analysis
Gemini 2.5 Flash (Reasoning)0.0888888888888889Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
GPT-5.6 Terra (low)0.0888888888888889Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
GPT-5.6 Luna (medium)0.0833333333333333Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemini 2.5 Flash (Non-reasoning)0.0833333333333333Not recordedNot recorded2025-05-20 · model_announcementArtificial Analysis
GLM-5.2 (max)0.0722222222222222Not recordedNot recorded2026-06-16 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, High Effort)0.0666666666666667Not recordedNot recorded2026-04-24 · model_announcementArtificial Analysis
GPT-5.6 Luna (low)0.0611111111111111Not recordedNot recorded2026-07-09 · model_announcementArtificial Analysis
Gemini 3.1 Flash-Lite0.0611111111111111Not recordedNot recorded2026-03-03 · model_announcementArtificial Analysis
GPT-5.4 nano (xhigh)0.05Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
Claude 4.5 Haiku (Non-reasoning)0.0444444444444444Not recordedNot recorded2025-10-15 · model_announcementArtificial Analysis
Nova 2.0 Pro Preview (medium)0.0388888888888889Not recordedNot recorded2025-11-27 · model_announcementArtificial Analysis
GPT-5.4 mini (xhigh)0.0388888888888889Not recordedNot recorded2026-03-17 · model_announcementArtificial Analysis
MiniMax-M2.70.0333333333333333Not recordedNot recorded2026-03-18 · model_announcementArtificial Analysis
Llama 4 Maverick0.0222222222222222Not recordedNot recorded2025-04-05 · model_announcementArtificial Analysis
Gemini 2.5 Flash-Lite (Reasoning)0.0222222222222222Not recordedNot recorded2025-06-17 · model_announcementArtificial Analysis
Mistral Medium 3.50.0166666666666667Not recordedNot recorded2026-04-29 · model_announcementArtificial Analysis
gpt-oss-120b (high)0.0111111111111111Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
gpt-oss-20b (high)0.00555555555555556Not recordedNot recorded2025-08-05 · model_announcementArtificial Analysis
Solar Pro 30.00555555555555556Not recordedNot recorded2026-04-06 · model_announcementArtificial Analysis
Nova Lite0Not recordedNot recorded2024-12-03 · model_announcementArtificial Analysis
GPT-4o mini0Not recordedNot recorded2024-07-18 · model_announcementArtificial Analysis

Put this benchmark in context

Reasoning and math benchmarks