Benchmark

CritPt

Physics reasoning

Categories
intelligence-index, reasoning, science
Openness
unknown
Source
artificial_analysis
Reported scores
492

Reported scores

artificial_analysis

ModelOrganizationReported valueReportedEvidence
A.X-K2SK Telecom0.08857142857142862026-08-12evidence
Agnes 2.5 Pro AlphaSapiens AI0.1085714285714292026-07-24evidence
Apertus 70B InstructSwiss AI Initiative02025-09-02evidence
Apertus 8B InstructSwiss AI Initiative02025-09-02evidence
Apriel-v1.5-15B-ThinkerServiceNow0.01142857142857142025-09-30evidence
Apriel-v1.6-15B-ThinkerServiceNow0.002857142857142862025-11-25evidence
Celeris-1Celeris02026-07-24evidence
Claude 3 HaikuAnthropic02024-03-04evidence
Claude 3.5 HaikuAnthropic02024-10-22evidence
Claude 3.7 Sonnet (Non-reasoning)Anthropic02025-02-24evidence
Claude 3.7 Sonnet (Reasoning)Anthropic0.008571428571428572025-02-24evidence
Claude 4 Sonnet (Non-reasoning)Anthropic0.01142857142857142025-05-22evidence
Claude 4 Sonnet (Reasoning)Anthropic0.002857142857142862025-05-22evidence
Claude 4.1 Opus (Reasoning)Anthropic02025-08-05evidence
Claude 4.5 Haiku (Non-reasoning)Anthropic02025-10-15evidence
Claude 4.5 Haiku (Reasoning)Anthropic02025-10-15evidence
Claude 4.5 Sonnet (Non-reasoning)Anthropic02025-09-29evidence
Claude 4.5 Sonnet (Reasoning)Anthropic0.01142857142857142025-09-29evidence
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic0.28571428572026-06-09evidence
Claude Opus 4.5 (Non-reasoning)Anthropic0.002857142857142862025-11-24evidence
Claude Opus 4.5 (Reasoning)Anthropic0.04571428571428572025-11-24evidence
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic0.1257142857142862026-02-05evidence
Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic0.02840816326530612026-02-05evidence
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic0.122026-04-16evidence
Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic0.05142857142857142026-04-16evidence
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic0.2085714285714292026-05-28evidence
Claude Opus 5 (Adaptive Reasoning, High Effort)Anthropic0.2828571428571432026-07-24evidence
Claude Opus 5 (Adaptive Reasoning, Low Effort)Anthropic0.2314285714285712026-07-24evidence
Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic0.2914285714285712026-07-24evidence
Claude Opus 5 (Adaptive Reasoning, Medium Effort)Anthropic0.2685714285714292026-07-24evidence
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic0.2771428571428572026-07-24evidence
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic0.03142857142857142026-02-17evidence
Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic0.008571428571428572026-02-17evidence
Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic0.008571428571428572026-02-17evidence
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic0.1685714285714292026-06-30evidence
Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic0.01142857142857142026-06-30evidence
Cogito v2.1 (Reasoning)Deep Cogito02025-11-18evidence
Command ACohere02025-03-13evidence
Command A+Cohere0.002857142857142862026-05-20evidence
DeepSeek R1 (Jan '25)DeepSeek0.005714285714285712025-01-20evidence
DeepSeek R1 0528 (May '25)DeepSeek0.01428571428571432025-05-28evidence
DeepSeek R1 0528 Qwen3 8BDeepSeek02025-05-29evidence
DeepSeek R1 Distill Llama 70BDeepSeek02025-01-20evidence
DeepSeek V3 (Dec '24)DeepSeek02024-12-26evidence
DeepSeek V3 0324DeepSeek02025-03-25evidence
DeepSeek V3.1 (Non-reasoning)DeepSeek02025-08-21evidence
DeepSeek V3.1 (Reasoning)DeepSeek0.022025-08-21evidence
DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek02025-09-22evidence
DeepSeek V3.1 Terminus (Reasoning)DeepSeek0.01714285714285712025-09-22evidence
DeepSeek V3.2 (Non-reasoning)DeepSeek0.008571428571428572025-12-01evidence
DeepSeek V3.2 (Reasoning)DeepSeek0.02857142857142862025-12-01evidence
DeepSeek V3.2 Exp (Non-reasoning)DeepSeek0.01428571428571432025-09-29evidence
DeepSeek V3.2 Exp (Reasoning)DeepSeek0.01428571428571432025-09-29evidence
DeepSeek V3.2 SpecialeDeepSeek0.07428571428571432025-12-01evidence
DeepSeek V4 Flash (Non-reasoning)DeepSeek0.002857142857142862026-04-24evidence
DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek0.03428571428571432026-04-24evidence
DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek0.07142857142857142026-04-24evidence
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek0.1657142857142862026-07-31evidence
DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek0.1085714285714292026-08-21evidence
DeepSeek V4 Pro (Non-reasoning)DeepSeek0.008571428571428572026-04-24evidence
DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek0.12026-04-24evidence
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek0.1285714285714292026-04-24evidence
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek0.182026-08-13evidence
Devstral 2Mistral02025-12-09evidence
Devstral MediumMistral02025-07-10evidence
Devstral Small (Jul '25)Mistral02025-07-10evidence
Devstral Small (May '25)Mistral02025-05-21evidence
Devstral Small 2Mistral02025-12-09evidence
DiffusionGemma 26B A4BGoogle0.002857142857142862026-06-10evidence
Doubao Seed CodeByteDance Seed0.002857142857142862025-11-11evidence
ERNIE 4.5 300B A47BBaidu02025-06-30evidence
ERNIE 5.0 Thinking PreviewBaidu0.01428571428571432025-11-13evidence
Exaone 4.0 1.2B (Non-reasoning)LG AI Research02025-07-15evidence
Exaone 4.0 1.2B (Reasoning)LG AI Research02025-07-15evidence
EXAONE 4.0 32B (Non-reasoning)LG AI Research02025-07-15evidence
EXAONE 4.0 32B (Reasoning)LG AI Research02025-07-15evidence
EXAONE 4.5 33BLG AI Research0.002857142857142862026-04-09evidence
Falcon-H1R-7BTII UAE0.002857142857142862026-01-04evidence
G9v3-39A5BAI9Stars0.002857142857142862026-08-20evidence
G9v3-3BAI9Stars02026-07-23evidence
Gemini 2.0 Flash (Feb '25)Google02025-02-05evidence
Gemini 2.5 Flash (Non-reasoning)Google0.01428571428571432025-05-20evidence
Gemini 2.5 Flash (Reasoning)Google0.01142857142857142025-05-20evidence
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)Google02025-09-25evidence
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)Google0.002857142857142862025-09-25evidence
Gemini 2.5 Flash-Lite (Non-reasoning)Google02025-06-17evidence
Gemini 2.5 Flash-Lite (Reasoning)Google02025-06-17evidence
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google02025-09-25evidence
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google02025-09-08evidence
Gemini 2.5 ProGoogle0.02571428571428572025-06-05evidence
Gemini 3 Deep ThinkGoogle0.2571428571428572026-02-05evidence
Gemini 3 Flash Preview (Non-reasoning)Google0.01428571428571432025-12-17evidence
Gemini 3 Flash Preview (Reasoning)Google0.08571428571428572025-12-17evidence
Gemini 3 Pro Preview (high)Google0.09142857142857142025-11-18evidence
Gemini 3 Pro Preview (low)Google02025-11-18evidence
Gemini 3.1 Flash-LiteGoogle0.01142857142857142026-03-03evidence
Gemini 3.1 Pro PreviewGoogle0.1771428571428572026-02-19evidence
Gemini 3.5 Flash (high)Google0.1314285714285712026-05-19evidence
Gemini 3.5 Flash (medium)Google0.1085714285714292026-05-19evidence
Gemini 3.5 Flash (minimal)Google0.01428571428571432026-05-19evidence
Gemini 3.5 Flash-LiteGoogle02026-07-21evidence
Gemini 3.6 Flash (high)Google0.1057142857142862026-07-21evidence
Gemini 3.7 Flash (high)Google0.1428571428571432026-08-13evidence
Gemini 3.7 Flash (low)Google0.05714285714285712026-08-13evidence
Gemini 3.7 Flash (medium)Google0.09428571428571432026-08-13evidence
Gemma 3 12B InstructGoogle02025-03-12evidence
Gemma 3 1B InstructGoogle02025-03-13evidence
Gemma 3 270MGoogle02025-08-14evidence
Gemma 3 27B InstructGoogle02025-03-12evidence
Gemma 3 4B InstructGoogle02025-03-12evidence
Gemma 3n E2B InstructGoogle02025-06-26evidence
Gemma 3n E4B InstructGoogle02025-06-26evidence
Gemma 4 12B (Non-reasoning)Google02026-06-03evidence
Gemma 4 12B (Reasoning)Google02026-06-03evidence
Gemma 4 26B A4B (Non-reasoning)Google02026-04-02evidence
Gemma 4 26B A4B (Reasoning)Google02026-04-02evidence
Gemma 4 31B (Non-reasoning)Google02026-04-02evidence
Gemma 4 31B (Reasoning)Google0.01428571428571432026-04-02evidence
Gemma 4 E2B (Non-reasoning)Google02026-04-02evidence
Gemma 4 E2B (Reasoning)Google02026-04-02evidence
Gemma 4 E4B (Non-reasoning)Google0.002857142857142862026-04-03evidence
Gemma 4 E4B (Reasoning)Google0.005714285714285712026-04-03evidence
GLM 5V Turbo (Reasoning)Z.ai0.005714285714285712026-04-01evidence
GLM-4.5 (Reasoning)Z.ai02025-07-28evidence
GLM-4.5-AirZ.ai02025-07-28evidence
GLM-4.5V (Non-reasoning)Z.ai02025-08-11evidence
GLM-4.5V (Reasoning)Z.ai02025-08-11evidence
GLM-4.6 (Non-reasoning)Z.ai02025-09-30evidence
GLM-4.6 (Reasoning)Z.ai0.01142857142857142025-09-30evidence
GLM-4.6V (Non-reasoning)Z.ai02025-12-08evidence
GLM-4.6V (Reasoning)Z.ai02025-12-08evidence
GLM-4.7 (Non-reasoning)Z.ai02025-12-22evidence
GLM-4.7 (Reasoning)Z.ai0.01710204081632652025-12-22evidence
GLM-4.7-Flash (Non-reasoning)Z.ai02026-01-19evidence
GLM-4.7-Flash (Reasoning)Z.ai0.002857142857142862026-01-19evidence
GLM-5 (Non-reasoning)Z.ai02026-02-11evidence
GLM-5 (Reasoning)Z.ai0.022026-02-11evidence
GLM-5-TurboZ.ai0.002857142857142862026-03-15evidence
GLM-5.1 (Non-reasoning)Z.ai02026-04-07evidence
GLM-5.1 (Reasoning)Z.ai0.04571428571428572026-04-07evidence
GLM-5.2 (max)Z.ai0.2085714285714292026-06-16evidence
GLM-5.2 (Non-reasoning)Z.ai0.03142857142857142026-06-16evidence
GLM-5.3 (max)Z.ai0.1914285714285712026-08-18evidence
GPT-4.1OpenAI02025-04-14evidence
GPT-4.1 miniOpenAI02025-04-14evidence
GPT-4.1 nanoOpenAI02025-04-14evidence
GPT-4o (Aug '24)OpenAI02024-08-06evidence
GPT-4o (Nov '24)OpenAI02024-11-20evidence
GPT-5 (high)OpenAI0.05714285714285712025-08-07evidence
GPT-5 (low)OpenAI0.01142857142857142025-08-07evidence
GPT-5 (medium)OpenAI02025-08-07evidence
GPT-5 (minimal)OpenAI02025-08-07evidence
GPT-5 Codex (high)OpenAI0.05142857142857142025-09-23evidence
GPT-5 mini (high)OpenAI02025-08-07evidence
GPT-5 mini (medium)OpenAI0.01428571428571432025-08-07evidence
GPT-5 mini (minimal)OpenAI02025-08-07evidence
GPT-5 nano (high)OpenAI02025-08-07evidence
GPT-5 nano (medium)OpenAI02025-08-07evidence
GPT-5 nano (minimal)OpenAI02025-08-07evidence
GPT-5.1 (high)OpenAI0.04857142857142862025-11-13evidence
GPT-5.1 (Non-reasoning)OpenAI02025-11-13evidence
GPT-5.1 Codex (high)OpenAI0.05714285714285712025-11-13evidence
GPT-5.1 Codex mini (high)OpenAI02025-11-13evidence
GPT-5.2 (medium)OpenAI0.07857142857142852025-12-11evidence
GPT-5.2 (Non-reasoning)OpenAI0.005714285714285712025-12-11evidence
GPT-5.2 (xhigh)OpenAI0.1155102040816332025-12-11evidence
GPT-5.2 Codex (xhigh)OpenAI0.08669387755102042025-12-11evidence
GPT-5.3 Codex (xhigh)OpenAI0.1685714285714292026-02-05evidence
GPT-5.4 (low)OpenAI0.07428571428571432026-03-05evidence
GPT-5.4 (Non-reasoning)OpenAI0.005714285714285712026-03-05evidence
GPT-5.4 (xhigh)OpenAI0.23428571432026-03-05evidence
GPT-5.4 mini (medium)OpenAI0.02857142857142862026-03-17evidence
GPT-5.4 mini (Non-Reasoning)OpenAI02026-03-17evidence
GPT-5.4 mini (xhigh)OpenAI0.12026-03-17evidence
GPT-5.4 nano (medium)OpenAI0.05142857142857142026-03-17evidence
GPT-5.4 nano (Non-Reasoning)OpenAI02026-03-17evidence
GPT-5.4 nano (xhigh)OpenAI0.09253061224489792026-03-17evidence
GPT-5.4 Pro (xhigh)OpenAI0.32026-03-05evidence
GPT-5.5 (high)OpenAI0.2542857142857142026-04-23evidence
GPT-5.5 (low)OpenAI0.082026-04-23evidence
GPT-5.5 (medium)OpenAI0.1857142857142862026-04-23evidence
GPT-5.5 (Non-reasoning)OpenAI0.01428571428571432026-04-23evidence
GPT-5.5 (xhigh)OpenAI0.2714285714285712026-04-23evidence
GPT-5.5 Instant (June 2026)OpenAI02026-06-25evidence
GPT-5.5 Instant (May 2026)OpenAI0.02571428571428572026-05-05evidence
GPT-5.5 Pro (xhigh)OpenAI0.3057142857142862026-04-23evidence
GPT-5.6 Luna (high)OpenAI0.1657142857142862026-07-09evidence
GPT-5.6 Luna (low)OpenAI0.02571428571428572026-07-09evidence
GPT-5.6 Luna (max)OpenAI0.2057142857142862026-07-09evidence
GPT-5.6 Luna (medium)OpenAI0.04857142857142862026-07-09evidence
GPT-5.6 Luna (Non-reasoning)OpenAI0.002857142857142862026-07-09evidence
GPT-5.6 Luna (xhigh)OpenAI0.2057142857142862026-07-09evidence
GPT-5.6 Sol (high)OpenAI0.2571428571428572026-07-09evidence
GPT-5.6 Sol (low)OpenAI0.1485714285714292026-07-09evidence
GPT-5.6 Sol (max)OpenAI0.3228571428571432026-07-09evidence
GPT-5.6 Sol (medium)OpenAI0.2285714285714292026-07-09evidence
GPT-5.6 Sol (Non-reasoning)OpenAI0.05142857142857142026-07-09evidence
GPT-5.6 Sol (xhigh)OpenAI0.2857142857142862026-07-09evidence
GPT-5.6 Terra (high)OpenAI0.2285714285714292026-07-09evidence
GPT-5.6 Terra (low)OpenAI0.09428571428571432026-07-09evidence
GPT-5.6 Terra (max)OpenAI0.32026-07-09evidence
GPT-5.6 Terra (medium)OpenAI0.1742857142857142026-07-09evidence
GPT-5.6 Terra (Non-reasoning)OpenAI0.022026-07-09evidence
GPT-5.6 Terra (xhigh)OpenAI0.2714285714285712026-07-09evidence
gpt-oss-120b (high)OpenAI0.01142857142857142025-08-05evidence
gpt-oss-120b (low)OpenAI02025-08-05evidence
gpt-oss-20b (high)OpenAI0.01428571428571432025-08-05evidence
gpt-oss-20b (low)OpenAI02025-08-05evidence
Granite 3.3 8B (Non-reasoning)IBM02025-04-16evidence
Granite 4.0 1BIBM02025-10-28evidence
Granite 4.0 350MIBM02025-10-28evidence
Granite 4.0 H 1BIBM02025-10-28evidence
Granite 4.0 H 350MIBM02025-10-28evidence
Granite 4.0 H SmallIBM02025-09-22evidence
Granite 4.0 MicroIBM02025-09-22evidence
Granite 4.1 30BIBM02026-04-29evidence
Granite 4.1 3BIBM02026-04-29evidence
Granite 4.1 8BIBM02026-04-29evidence
Grok 3xAI02025-02-19evidence
Grok 3 mini Reasoning (high)xAI0.005714285714285712025-02-19evidence
Grok 4xAI0.022025-07-10evidence
Grok 4 Fast (Non-reasoning)xAI02025-09-19evidence
Grok 4 Fast (Reasoning)xAI0.02857142857142862025-09-19evidence
Grok 4.1 Fast (Non-reasoning)xAI02025-11-19evidence
Grok 4.1 Fast (Reasoning)xAI0.02857142857142862025-11-19evidence
Grok 4.20 0309 (Non-reasoning)xAI02026-03-10evidence
Grok 4.20 0309 (Reasoning)xAI0.062026-03-10evidence
Grok 4.20 0309 v2 (Non-reasoning)xAI0.002857142857142862026-04-07evidence
Grok 4.20 0309 v2 (Reasoning)xAI0.06571428571428572026-04-07evidence
Grok 4.3 (high)xAI0.082026-04-30evidence
Grok 4.3 (low)xAI0.005714285714285712026-04-30evidence
Grok 4.3 (medium)xAI0.04857142857142862026-04-30evidence
Grok 4.3 (Non-reasoning)xAI02026-04-30evidence
Grok 4.5 (high)xAI0.1542857142857142026-07-08evidence
Grok 4.6 (high)xAI0.1714285714285712026-08-12evidence
Grok 4.6 (low)xAI0.05714285714285712026-08-12evidence
Grok 4.6 (medium)xAI0.1771428571428572026-08-12evidence
Grok 4.6 (xhigh)xAI0.1971428571428572026-08-12evidence
Grok Build 0.1 0616xAI0.09142857142857142026-06-16evidence
Grok Code Fast 1xAI02025-08-28evidence
Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research02025-08-27evidence
Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research0.002857142857142862025-08-27evidence
Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research02025-08-27evidence
Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research02025-08-27evidence
Hy3Tencent0.04857142857142862026-07-06evidence
Hy3-preview (Non-reasoning)Tencent0.002857142857142862026-04-23evidence
Hy3-preview (Reasoning)Tencent0.04571428571428572026-04-23evidence
HyperCLOVA X SEED Think (32B)Naver02025-12-26evidence
HyperNova 60B 2605Multiverse Computing0.008571428571428572026-05-26evidence
Inkling (xhigh)Thinking Machines0.05428571428571432026-07-15evidence
Inkling SmallThinking Machines0.08285714285714292026-07-30evidence
INTELLECT-3Prime Intellect0.002857142857142862025-11-27evidence
Jamba 1.7 LargeAI21 Labs02025-07-07evidence
Jamba 1.7 MiniAI21 Labs02025-07-07evidence
Jamba Reasoning 3BAI21 Labs02025-10-08evidence
JT-35B-FlashChina Mobile02026-05-14evidence
JT-4.1 Flash 236B A21BChina Mobile02026-07-09evidence
JT-MINIChina Mobile02026-04-15evidence
K-EXAONE (Non-reasoning)LG AI Research02025-12-31evidence
K-EXAONE (Reasoning)LG AI Research0.01118367346938782025-12-31evidence
K-EXAONE 2.0 0803LG AI Research0.008571428571428572026-08-12evidence
K2 Think V2MBZUAI Institute of Foundation Models02025-12-15evidence
K2-V2 (high)MBZUAI Institute of Foundation Models02025-12-05evidence
K2-V2 (low)MBZUAI Institute of Foundation Models02025-12-05evidence
K2-V2 (medium)MBZUAI Institute of Foundation Models02025-12-05evidence
KAT Coder Pro V2KwaiKAT02026-03-27evidence
KAT-Coder-Pro V1KwaiKAT02025-11-11evidence
Kimi K2Moonshot AI02025-07-11evidence
Kimi K2 0905Moonshot AI02025-09-05evidence
Kimi K2 ThinkingMoonshot AI0.02571428571428572025-11-06evidence
Kimi K2.5 (Non-reasoning)Moonshot AI0.005714285714285712026-01-27evidence
Kimi K2.5 (Reasoning)Moonshot AI0.03142857142857142026-01-27evidence
Kimi K2.6Moonshot AI0.082026-04-20evidence
Kimi K2.6 (Non-reasoning)Moonshot AI0.01428571428571432026-04-20evidence
Kimi K2.7 CodeMoonshot AI0.12026-06-12evidence
Kimi K3 (low)Moonshot AI0.03142857142857142026-07-16evidence
Kimi K3 (max)Moonshot AI0.2342857142857142026-07-16evidence
LFM2 1.2BLiquid AI02025-07-10evidence
LFM2 2.6BLiquid AI02025-09-23evidence
LFM2 24B A2BLiquid AI02026-02-25evidence
LFM2 8B A1BLiquid AI02025-10-07evidence
LFM2.5-1.2B-InstructLiquid AI02026-01-05evidence
LFM2.5-1.2B-ThinkingLiquid AI02026-01-20evidence
LFM2.5-2.6BLiquid AI02026-08-04evidence
LFM2.5-8B-A1BLiquid AI02026-05-28evidence
LFM2.5-VL-1.6BLiquid AI02026-01-05evidence
Ling 2.6 FlashInclusionAI02026-04-21evidence
Ling 3.0 FlashInclusionAI0.01714285714285712026-08-04evidence
Ling 3.0 TinyInclusionAI02026-08-06evidence
Ling-1TInclusionAI0.005714285714285712025-10-08evidence
Ling-2.6-1TInclusionAI0.002857142857142862026-04-23evidence
Ling-flash-2.0InclusionAI02025-09-17evidence
Ling-mini-2.0InclusionAI02025-09-09evidence
Llama 3 Instruct 70BMeta02024-04-18evidence
Llama 3 Instruct 8BMeta02024-04-18evidence
Llama 3.1 Instruct 405BMeta02024-07-23evidence
Llama 3.1 Instruct 70BMeta02024-07-23evidence
Llama 3.1 Instruct 8BMeta02024-07-23evidence
Llama 3.1 Nemotron Instruct 70BNVIDIA02024-10-15evidence
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA02025-04-07evidence
Llama 3.2 Instruct 11B (Vision)Meta02024-09-25evidence
Llama 3.2 Instruct 1BMeta02024-09-25evidence
Llama 3.3 Instruct 70BMeta02024-12-06evidence
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA02025-03-18evidence
Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA02025-03-18evidence
Llama 4 MaverickMeta02025-04-05evidence
Llama 4 ScoutMeta02025-04-05evidence
Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA02025-07-25evidence
Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA02025-07-25evidence
LongCat 2.0LongCat0.02571428571428572026-06-29evidence
LongCat Flash LiteLongCat02026-01-28evidence
Magistral Medium 1Mistral0.002857142857142862025-06-10evidence
Magistral Medium 1.2Mistral0.002857142857142862025-09-18evidence
Magistral Small 1Mistral02025-06-10evidence
Magistral Small 1.2Mistral0.002857142857142862025-09-17evidence
Mercury 2Inception0.008489795918367352026-02-20evidence
Mi:dm K 2.5 ProKorea Telecom02025-12-11evidence
Mi:dm K 2.5 Pro PreviewKorea Telecom02025-12-11evidence
MiMo-V2-Flash (Feb 2026)Xiaomi0.02857142857142862025-12-16evidence
MiMo-V2-Flash (Non-reasoning)Xiaomi02025-12-16evidence
MiMo-V2-Flash (Reasoning)Xiaomi0.04285714285714292025-12-16evidence
MiMo-V2-OmniXiaomi0.01142857142857142026-03-19evidence
MiMo-V2-Omni-0327Xiaomi0.008571428571428572026-03-27evidence
MiMo-V2-ProXiaomi0.002857142857142862026-03-18evidence
MiMo-V2.5Xiaomi0.03714285714285712026-04-22evidence
MiMo-V2.5-ProXiaomi0.042026-04-22evidence
MiMo-V2.5-Pro (Non-reasoning)Xiaomi0.01142857142857142026-04-22evidence
MiniCPM-V 4.6 1.3BOpenBMB02026-05-11evidence
MiniCPM5-1B (Non-reasoning)OpenBMB02026-05-25evidence
MiniCPM5-1B (Reasoning)OpenBMB02026-05-25evidence
MiniMax M1 80kMiniMax02025-06-17evidence
MiniMax-M2MiniMax0.008571428571428572025-10-26evidence
MiniMax-M2.1MiniMax0.002857142857142862025-12-23evidence
MiniMax-M2.5MiniMax0.01142857142857142026-02-12evidence
MiniMax-M2.7MiniMax0.005714285714285712026-03-18evidence
MiniMax-M3MiniMax0.03714285714285712026-06-01evidence
Ministral 3 14BMistral02025-12-02evidence
Ministral 3 3BMistral02025-12-02evidence
Ministral 3 8BMistral02025-12-02evidence
Mistral 7B InstructMistral02023-09-27evidence
Mistral Large 2 (Nov '24)Mistral02024-11-18evidence
Mistral Large 3Mistral02025-12-02evidence
Mistral Medium 3Mistral02025-05-07evidence
Mistral Medium 3.1Mistral02025-08-12evidence
Mistral Medium 3.5Mistral02026-04-29evidence
Mistral Small 3.1Mistral02025-03-17evidence
Mistral Small 3.2Mistral02025-06-20evidence
Mistral Small 4 (Non-reasoning)Mistral0.002857142857142862026-03-16evidence
Mistral Small 4 (Reasoning)Mistral0.002857142857142862026-03-16evidence
Molmo2-8BAllen Institute for AI02025-12-11evidence
Motif 3Motif Technologies0.06571428571428572026-08-12evidence
Motif 3 (Beta)Motif Technologies0.062026-07-14evidence
Motif-2-12.7B-ReasoningMotif Technologies02025-12-04evidence
Muse Glimmer (high)Meta0.02571428571428572026-08-10evidence
Muse SparkMeta0.113306122448982026-04-08evidence
Muse Spark 1.1 (xhigh)Meta0.1514285714285712026-07-09evidence
Muse Spark 1.2 (xhigh)Meta0.1771428571428572026-08-05evidence
Nanbeige4.1-3BNanbeige02026-02-11evidence
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA02026-04-29evidence
Nemotron 3 Super 120B A12B (Reasoning)NVIDIA0.03142857142857142026-03-11evidence
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA0.03142857142857142026-06-04evidence
Nemotron 3.5 LightningNVIDIA02026-08-11evidence
Nemotron Cascade 2 30B A3BNVIDIA0.005714285714285712026-03-19evidence
Nex-N2-ProNex AGI0.08571428571428572026-06-02evidence
North Mini CodeCohere0.002857142857142862026-06-09evidence
Nova 2.0 Lite (high)Amazon0.002857142857142862025-10-29evidence
Nova 2.0 Lite (low)Amazon02025-10-29evidence
Nova 2.0 Lite (medium)Amazon02025-10-29evidence
Nova 2.0 Lite (Non-reasoning)Amazon02025-10-29evidence
Nova 2.0 Omni (low)Amazon02025-11-26evidence
Nova 2.0 Omni (medium)Amazon02025-11-26evidence
Nova 2.0 Omni (Non-reasoning)Amazon02025-11-26evidence
Nova 2.0 Pro Preview (low)Amazon02025-11-27evidence
Nova 2.0 Pro Preview (medium)Amazon02025-11-27evidence
Nova 2.0 Pro Preview (Non-reasoning)Amazon02025-11-27evidence
Nova LiteAmazon02024-12-03evidence
Nova MicroAmazon02024-12-03evidence
Nova PremierAmazon02025-04-30evidence
Nova ProAmazon02024-12-03evidence
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA02025-12-15evidence
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA0.008571428571428572025-12-15evidence
NVIDIA Nemotron 3 Nano 4BNVIDIA02026-03-16evidence
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA02025-10-28evidence
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA02025-10-28evidence
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA02025-08-18evidence
NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA02025-08-18evidence
o1OpenAI0.002857142857142862024-12-05evidence
o3OpenAI0.01142857142857142025-04-16evidence
o3-mini (high)OpenAI0.002857142857142862025-01-31evidence
o4-mini (high)OpenAI0.005714285714285712025-04-16evidence
Olmo 3 32B ThinkAllen Institute for AI02025-11-20evidence
Olmo 3 7B InstructAllen Institute for AI02025-11-20evidence
Olmo 3 7B ThinkAllen Institute for AI02025-11-20evidence
Olmo 3.1 32B InstructAllen Institute for AI02026-01-13evidence
Olmo 3.1 32B ThinkAllen Institute for AI02025-12-12evidence
Phi-4Microsoft02024-12-12evidence
Phi-4 Mini InstructMicrosoft02024-02-26evidence
Qwen2.5 Instruct 72BQwen02024-09-19evidence
Qwen3 0.6B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 0.6B (Reasoning)Qwen02025-04-28evidence
Qwen3 1.7B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 1.7B (Reasoning)Qwen02025-04-28evidence
Qwen3 14B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 14B (Reasoning)Qwen02025-04-28evidence
Qwen3 235B A22B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 235B A22B (Reasoning)Qwen02025-04-28evidence
Qwen3 235B A22B 2507 (Reasoning)Qwen02025-07-25evidence
Qwen3 235B A22B 2507 InstructQwen02025-07-21evidence
Qwen3 30B A3B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 30B A3B (Reasoning)Qwen02025-04-28evidence
Qwen3 30B A3B 2507 (Reasoning)Qwen0.002857142857142862025-07-30evidence
Qwen3 30B A3B 2507 InstructQwen02025-07-29evidence
Qwen3 32B (Reasoning)Qwen0.002857142857142862025-04-28evidence
Qwen3 4B 2507 (Reasoning)Qwen02025-08-06evidence
Qwen3 4B 2507 InstructQwen02025-08-06evidence
Qwen3 8B (Non-reasoning)Qwen02025-04-28evidence
Qwen3 8B (Reasoning)Qwen02025-04-28evidence
Qwen3 Coder 30B A3B InstructQwen02025-07-31evidence
Qwen3 Coder 480B A35B InstructQwen02025-07-22evidence
Qwen3 Coder NextQwen02026-02-03evidence
Qwen3 MaxQwen02025-09-23evidence
Qwen3 Max (Preview)Qwen0.008571428571428572025-09-05evidence
Qwen3 Max ThinkingQwen0.01714285714285712026-01-26evidence
Qwen3 Max Thinking (Preview)Qwen02025-11-03evidence
Qwen3 Next 80B A3B (Reasoning)Qwen02025-09-11evidence
Qwen3 Next 80B A3B InstructQwen02025-09-11evidence
Qwen3 Omni 30B A3B (Reasoning)Qwen02025-09-22evidence
Qwen3 Omni 30B A3B InstructQwen02025-09-22evidence
Qwen3 VL 235B A22B (Reasoning)Qwen02025-09-23evidence
Qwen3 VL 235B A22B InstructQwen02025-09-23evidence
Qwen3 VL 30B A3B (Reasoning)Qwen02025-10-03evidence
Qwen3 VL 30B A3B InstructQwen02025-10-03evidence
Qwen3 VL 32B (Reasoning)Qwen02025-10-21evidence
Qwen3 VL 32B InstructQwen02025-10-21evidence
Qwen3 VL 4B (Reasoning)Qwen02025-10-14evidence
Qwen3 VL 4B InstructQwen02025-10-14evidence
Qwen3 VL 8B (Reasoning)Qwen0.002857142857142862025-10-14evidence
Qwen3 VL 8B InstructQwen02025-10-14evidence
Qwen3.5 0.8B (Non-reasoning)Qwen02026-03-02evidence
Qwen3.5 0.8B (Reasoning)Qwen02026-03-02evidence
Qwen3.5 122B A10B (Non-reasoning)Qwen0.008571428571428572026-02-24evidence
Qwen3.5 122B A10B (Reasoning)Qwen0.005714285714285712026-02-24evidence
Qwen3.5 27B (Non-reasoning)Qwen0.002857142857142862026-02-24evidence
Qwen3.5 27B (Reasoning)Qwen0.008530612244897962026-02-24evidence
Qwen3.5 2B (Non-reasoning)Qwen02026-03-02evidence
Qwen3.5 2B (Reasoning)Qwen02026-03-02evidence
Qwen3.5 35B A3B (Non-reasoning)Qwen0.005714285714285712026-02-24evidence
Qwen3.5 35B A3B (Reasoning)Qwen0.008571428571428572026-02-24evidence
Qwen3.5 397B A17B (Non-reasoning)Qwen0.008571428571428572026-02-16evidence
Qwen3.5 397B A17B (Reasoning)Qwen0.01706122448979592026-02-16evidence
Qwen3.5 4B (Non-reasoning)Qwen02026-03-02evidence
Qwen3.5 4B (Reasoning)Qwen02026-03-02evidence
Qwen3.5 9B (Non-reasoning)Qwen0.005714285714285712026-03-02evidence
Qwen3.5 9B (Reasoning)Qwen0.002857142857142862026-03-02evidence
Qwen3.5 Omni FlashQwen02026-03-30evidence
Qwen3.5 Omni PlusQwen0.005632653061224492026-03-30evidence
Qwen3.6 27B (Non-reasoning)Qwen0.008571428571428572026-04-22evidence
Qwen3.6 27B (Reasoning)Qwen0.01142857142857142026-04-22evidence
Qwen3.6 35B A3B (Non-reasoning)Qwen02026-04-16evidence
Qwen3.6 35B A3B (Reasoning)Qwen0.002857142857142862026-04-16evidence
Qwen3.6 Max PreviewQwen0.03706122448979592026-04-20evidence
Qwen3.6 PlusQwen0.02857142857142862026-04-02evidence
Qwen3.7 MaxQwen0.1342857142857142026-05-19evidence
Qwen3.7 PlusQwen0.09142857142857142026-06-01evidence
Qwen3.8 2.4T A95BQwen0.22026-08-12evidence
Qwen3.8 27B (low)Qwen02026-08-14evidence
Qwen3.8 27B (medium)Qwen02026-08-14evidence
Qwen3.8 27B (Non-reasoning)Qwen0.002857142857142862026-08-14evidence
Qwen3.8 27B (xhigh)Qwen0.05428571428571432026-08-14evidence
Qwen3.8 MaxQwen0.22026-08-03evidence
Reka Flash 3Reka AI02025-03-10evidence
Ring-1TInclusionAI0.005714285714285712025-10-13evidence
Ring-2.6-1TInclusionAI0.03714285714285712026-05-08evidence
Ring-flash-2.0InclusionAI0.002775510204081632025-09-19evidence
Sarvam 105B (high)Sarvam02026-03-06evidence
Sarvam 30B (high)Sarvam0.002857142857142862026-03-06evidence
Sarvam M (Reasoning)Sarvam02025-05-23evidence
Seed-OSS-36B-InstructByteDance Seed02025-08-20evidence
Solar Open 100B (Reasoning)Upstage02025-12-17evidence
Solar Open2 250BUpstage0.05714285714285712026-08-12evidence
Solar Pro 2 (Non-reasoning)Upstage02025-07-09evidence
Solar Pro 2 (Reasoning)Upstage02025-07-09evidence
Solar Pro 3Upstage02026-04-06evidence
Solar Pro 4Upstage0.05428571428571432026-08-06evidence
Step 3.5 FlashStepFun0.02469387755102042026-02-02evidence
Step 3.5 Flash 2603StepFun0.02285714285714292026-04-02evidence
Step 3.7 FlashStepFun0.02285714285714292026-05-29evidence
Step3 VL 10BStepFun02026-01-20evidence
Tiny Aya GlobalCohere02026-02-17evidence
Tri-21B-ThinkTrillion Labs0.002857142857142862026-02-10evidence
Tri-21B-think PreviewTrillion Labs02026-02-10evidence
Trinity Large ThinkingArcee AI0.008571428571428572026-04-01evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.