BenchmarkActivecategory · knowledgefamily · humanitys-last-exam · variant full
data quality57
Updated 5 h ago · first seen 11 Sept 2026
- Metric
- accuracy · % ↑
- Current results
- 1,217
- Models
- 453
- Current leader
- Claude Fable 5.1 59.1%
Score history · solar-open-100b-reasoning 2 rows
- solar-open-100b-reasoning
- 10.43%aa_slug=solar-open-100b-reasoning · evaluator=Artificial Analysis · reasoning=on · index_version=4.312 Sept 2026
- 10.43%aa_slug=solar-open-100b-reasoning · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
Frontier over time · accuracy · evaluator=Artificial Analysis
9 leader changes recorded, all dated 11 Sept 2026 — the frontier line needs at least two distinct dates. The corpus is young: every result was first observed on the same day, so leader changes will separate in time as sources are re-crawled.
- 59.1%Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 58.7%Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 55.9%Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 55.5%Claude Fable 5 Anthropic Independent11 Sept 2026
- 53.1%gpt-6-astra OpenAI Independent11 Sept 2026
- 52.7%gpt-6-astra OpenAI Independent11 Sept 2026
- 51.3%Claude Opus 5 Anthropic Independent11 Sept 2026
- 11.0%grok-3-mini-reasoning SpaceXAI Independent11 Sept 2026
Includes closed rows (history). A point is emitted whenever a result beats every earlier result of the same group, ordered by evaluated_at when the source publishes it, else observed_at.
Leaderboard 453 models
Select models with +, then Compare.
| # | Model | Score | Trust | Configuration | vs leader | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1ClosedAnthropic · Claude · best of 10 rows | 59.1% | Independent | reasoning_effortmax | leader | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 2 | Claude Fable 5ClosedAnthropic · Claude · best of 2 rows | 55.5% | Independent | reasoningon | Partially comparable-3.66 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 3 | Claude Opus 5ClosedAnthropic · Claude · best of 10 rows | 54.9% | Independent | reasoning_effortmax | Comparable-4.26 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 4 | gpt-6-astraClosedOpenAI · GPT 6 · best of 11 rows | 54.7% | Independent | reasoning_effortmax | Comparable-4.45 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 5 | gpt-5.6-solClosedOpenAI · GPT 5.6 · best of 12 rows | 49.5% | Independent | reasoning_effortmax | Comparable-9.64 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 6 | Muse Spark 1.3ClosedMeta AI · best of 4 rows | 48.7% | Independent | reasoning_effortmax | Comparable-10.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 7 | Claude Opus 4.8ClosedAnthropic · Claude · best of 2 rows | 48.7% | Independent | reasoning_effortmax | Comparable-10.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 8 | Gemini 3.7 FlashClosedGoogle · Gemini 3.7 · best of 6 rows | 47.9% | Independent | reasoning_efforthigh | Partially comparable-11.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 9 | Gemini 3.8 FlashClosedGoogle · Gemini 3.8 · best of 6 rows | 47.8% | Independent | reasoning_efforthigh | Partially comparable-11.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 10 | Gemini 3.1 Pro PreviewClosedGoogle · Gemini 3.1 · best of 2 rows | 47.0% | Independent | reasoningon | Partially comparable-12.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 11 | Kimi K3Open weightsMoonshot AI · Kimi · best of 4 rows | 46.9% | Independent | reasoning_effortmax | Comparable-12.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 12 | Muse Spark 1.1ClosedMeta AI · best of 2 rows | 46.2% | Independent | reasoning_effortxhigh | Partially comparable-12.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 13 | gpt-5.5ClosedOpenAI · GPT 5.5 · best of 10 rows | 45.8% | Independent | reasoning_effortxhigh | Partially comparable-13.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 14 | Muse Spark 1.2ClosedMeta AI · best of 2 rows | 45.5% | Independent | reasoning_effortxhigh | Partially comparable-13.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 15 | Grok 4.6ClosedxAI · Grok · best of 8 rows | 44.1% | Independent | reasoning_effortxhigh | Partially comparable-15.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 16 | gpt-5.4ClosedOpenAI · GPT 5.4 · best of 6 rows | 43.7% | Independent | reasoning_effortxhigh | Partially comparable-15.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 17 | Qwen 3.8 MaxClosedQwen · Qwen3.8 · best of 2 rows | 43.0% | Independent | reasoningon | Partially comparable-16.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 18 | gpt-5.6-terraClosedOpenAI · GPT 5.6 · best of 12 rows | 42.9% | Independent | reasoning_effortmax | Comparable-16.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 19 | Gemini 3.5 FlashClosedGoogle · Gemini 3.5 · best of 6 rows | 42.7% | Independent | reasoningon | Partially comparable-16.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 19 | Grok 4.5ClosedxAI · Grok · best of 2 rows | 42.7% | Independent | reasoning_efforthigh | Partially comparable-16.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 21 | gpt-5.3-codexClosedOpenAI · GPT 5.3 · best of 2 rows | 42.5% | Independent | reasoning_effortxhigh | Partially comparable-16.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 22 | Qwen3.8 2.4T A95BOpen weightsQwen · Qwen3.8 · best of 2 rows | 42.5% | Independent | reasoningon | Partially comparable-16.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 23 | Claude Opus 4.7ClosedAnthropic · Claude · best of 4 rows | 42.3% | Independent | reasoning_effortmax | Comparable-16.8 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 24 | GLM 5.3Open weightsZ.ai (Zhipu AI) · GLM5.3 · best of 2 rows | 42.3% | Independent | reasoning_effortmax | Comparable-16.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 25 | Claude Sonnet 5ClosedAnthropic · Claude · best of 12 rows | 41.3% | Independent | reasoning_effortmax | Comparable-17.8 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 26 | Z.ai GLM 5.2Open weightsZ.ai (Zhipu AI) · GLM5.2 · best of 4 rows | 41.1% | Independent | reasoning_effortmax | Comparable-18.0 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 27 | deepseek-v4-proClosedDeepSeek · V4 · best of 2 rows | 41.0% | Independent | reasoning_effortmax | Comparable-18.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 28 | Gemini 3.6 FlashClosedGoogle · Gemini 3.6 · best of 2 rows | 40.8% | Independent | reasoningon | Partially comparable-18.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 29 | muse-sparkClosedMeta AI · best of 2 rows | 40.7% | Independent | reasoningon | Partially comparable-18.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 30 | Qwen3.7 MaxClosedQwen · Qwen3.7 · best of 2 rows | 40.5% | Independent | reasoningon | Partially comparable-18.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 31 | motif-0714ClosedMotif Technologies · best of 2 rows | 40.4% | Independent | reasoningon | Partially comparable-18.8 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 32 | Claude Opus 4.6ClosedAnthropic · Claude · best of 4 rows | 39.9% | Independent | reasoningadaptivereasoning_effortmax | Partially comparable-19.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 33 | GLM 5.3 FlashOpen weightsZ.ai (Zhipu AI) · GLM5.3 · best of 2 rows | 39.9% | Independent | reasoningon | Partially comparable-19.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 34 | gemini-3-proClosedGoogle · Gemini 3 · best of 4 rows | 39.7% | Independent | reasoning_efforthigh | Partially comparable-19.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 35 | gpt-5.6-lunaClosedOpenAI · GPT 5.6 · best of 12 rows | 39.5% | Independent | reasoning_effortmax | Comparable-19.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 36 | DeepSeek-V4.1-FlashOpen weightsDeepSeek · DeepSeek · best of 2 rows | 39.3% | Independent | reasoning_effortmax | Comparable-19.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 37 | MiniMax-M3Open weightsMiniMax · MiniMax · best of 2 rows | 39.0% | Independent | reasoningon | Partially comparable-20.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 38 | deepseek-v4-flashOpen weightsDeepSeek · DeepSeek · best of 2 rows | 38.5% | Independent | reasoning_effortmax | Comparable-20.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 39 | agnes-3-0-flashClosedSapiens AI · best of 2 rows | 38.5% | Independent | reasoningon | Partially comparable-20.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 40 | grok-build-0-1-06-16ClosedSpaceXAI · Grok · best of 2 rows | 38.3% | Independent | reasoningon | Partially comparable-20.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 41 | Qwen3.8 FlashOpen weightsQwen · Qwen3.8 · best of 2 rows | 38.0% | Independent | reasoningon | Partially comparable-21.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 42 | gpt-5.2ClosedOpenAI · GPT 5.2 · best of 6 rows | 37.7% | Independent | reasoning_effortxhigh | Partially comparable-21.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 43 | agnes-2-5-pro-betaClosedSapiens AI · best of 2 rows | 37.5% | Independent | reasoningon | Partially comparable-21.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 43 | deepseek-v4-pro-0424Open weightsDeepSeek · DeepSeek · best of 4 rows | 37.5% | Independent | reasoning_effortmax | Comparable-21.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 45 | Kimi K2.6Open weightsMoonshot AI · Kimi · best of 4 rows | 37.5% | Independent | reasoningon | Partially comparable-21.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 46 | Grok 4.3ClosedxAI · Grok · best of 8 rows | 37.2% | Independent | reasoning_efforthigh | Partially comparable-21.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 47 | motif-3Open weightsMotif Technologies · best of 2 rows | 37.0% | Independent | reasoningon | Partially comparable-22.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 48 | Gemini 3 Flash PreviewClosedGoogle · Gemini 3 | 36.6% | Independent | group defaults | Partially comparable-22.6 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 48 | gemini-3-flashClosedGoogle · Gemini 3 · best of 3 rows | 36.6% | Independent | reasoningon | Partially comparable-22.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 50 | GPT-5.2-CodexClosedOpenAI · GPT 5.2 · best of 2 rows | 35.7% | Independent | reasoning_effortxhigh | Partially comparable-23.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 51 | MiMo-V2.5-ProOpen weightsXiaomi · best of 4 rows | 35.7% | Independent | reasoningon | Partially comparable-23.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 52 | Qwen 3.7 PlusClosedQwen · Qwen3.7 · best of 2 rows | 35.6% | Independent | reasoningon | Partially comparable-23.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 53 | deepseek-v4-pro-0424-highOpen weightsDeepSeek · DeepSeek | 35.2% | Independent | group defaults | Partially comparable-23.9 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 54 | Kimi K2.7 CodeOpen weightsMoonshot AI · Kimi · best of 2 rows | 35.0% | Independent | reasoningon | Partially comparable-24.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 55 | deepseek-v4-flash-0420Open weightsDeepSeek · DeepSeek · best of 4 rows | 34.9% | Independent | reasoning_effortmax | Comparable-24.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 56 | Grok 4.20ClosedxAI · Grok · best of 3 rows | 34.5% | Independent | reasoningon | Partially comparable-24.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 57 | deepseek-v4-flash-visionClosedDeepSeek · DeepSeek · best of 2 rows | 34.5% | Independent | reasoning_effortmax | Comparable-24.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 58 | apodex-1-1ClosedApodex · best of 2 rows | 34.1% | Independent | reasoningon | Partially comparable-25.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 59 | Qwen3.8 27BOpen weightsQwen · Qwen3.8 · best of 8 rows | 33.9% | Independent | reasoning_effortxhigh | Partially comparable-25.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 60 | nex-n2-proOpen weightsNex AGI · best of 2 rows | 33.7% | Independent | reasoningon | Partially comparable-25.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 61 | LongCat 2.0Open weightsMeituan · best of 2 rows | 33.7% | Independent | reasoningon | Partially comparable-25.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 62 | kat-coder-pro-v1ClosedKwaiKAT · best of 2 rows | 33.6% | Independent | reasoningoff | Partially comparable-25.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 63 | Claude Sonnet 4.6ClosedAnthropic · Claude · best of 5 rows | 33.6% | Independent | reasoningadaptivereasoning_effortmax | Partially comparable-25.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 63 | agnes-2-5-pro-alphaOpen weightsSapiens AI · best of 2 rows | 33.6% | Independent | reasoningon | Partially comparable-25.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 65 | Hy3Open weightsTencent · best of 5 rows | 33.5% | Independent | reasoningon | Partially comparable-25.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 66 | Inkling SmallOpen weightsThinking Machines · best of 2 rows | 33.3% | Independent | reasoningon | Partially comparable-25.8 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 67 | grok-4-20-0309ClosedSpaceXAI · Grok 4.20 · best of 4 rows | 32.4% | Independent | reasoningon | Partially comparable-26.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 68 | k2-horizon-375b-a23bOpen weightsMBZUAI Institute of Foundation Models · best of 2 rows | 32.0% | Independent | reasoningon | Partially comparable-27.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 69 | InklingOpen weightsThinking Machines · best of 2 rows | 31.9% | Independent | reasoningon | Partially comparable-27.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 70 | Qwen3.6 Max PreviewClosedQwen · Qwen3.6 · best of 2 rows | 30.8% | Independent | reasoningon | Partially comparable-28.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 71 | Kimi K2.5Open weightsMoonshot AI · Kimi · best of 4 rows | 30.7% | Independent | reasoningon | Partially comparable-28.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 72 | mimo-v2-proClosedXiaomi · best of 2 rows | 30.4% | Independent | reasoningon | Partially comparable-28.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 73 | deepseek-v4-flash-0420-highOpen weightsDeepSeek · DeepSeek | 30.3% | Independent | group defaults | Partially comparable-28.9 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 74 | Claude Opus 4.5ClosedAnthropic · Claude · best of 4 rows | 30.1% | Independent | reasoningon | Partially comparable-29.0 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 75 | GLM 5.1Open weightsZ.ai (Zhipu AI) · GLM5.1 · best of 4 rows | 30.1% | Independent | reasoningon | Partially comparable-29.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 76 | MiniMax M2.7Open weightsMiniMax · MiniMax · best of 2 rows | 29.6% | Independent | reasoningon | Partially comparable-29.5 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 77 | a-x-k2Open weightsSK Telecom · best of 2 rows | 29.6% | Independent | reasoningon | Partially comparable-29.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 78 | GLM 5Open weightsZ.ai (Zhipu AI) · GLM5 · best of 4 rows | 29.3% | Independent | reasoningon | Partially comparable-29.8 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 79 | Solar Pro 4ClosedUpstage · Solar · best of 2 rows | 29.2% | Independent | reasoningon | Partially comparable-29.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 80 | Qwen3.5 397B A17BOpen weightsQwen · Qwen3.5 · best of 4 rows | 29.0% | Independent | reasoningon | Partially comparable-30.2 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 81 | deepseek-v3-2-specialeOpen weightsDeepSeek · DeepSeek · best of 2 rows | 28.7% | Independent | reasoningon | Partially comparable-30.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 82 | solar-open2-250bOpen weightsUpstage · Solar · best of 2 rows | 28.5% | Independent | reasoningon | Partially comparable-30.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 83 | gpt-5ClosedOpenAI · GPT 5 · best of 8 rows | 28.5% | Independent | reasoning_efforthigh | Partially comparable-30.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 83 | gpt-5.1ClosedOpenAI · GPT 5.1 · best of 4 rows | 28.5% | Independent | reasoning_efforthigh | Partially comparable-30.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 85 | Nemotron 3 UltraOpen weightsNVIDIA · Nemotron 3 · best of 2 rows | 28.4% | Independent | reasoningon | Partially comparable-30.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 86 | gpt-5.4-nanoClosedOpenAI · GPT 5.4 · best of 6 rows | 28.3% | Independent | reasoning_effortxhigh | Partially comparable-30.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 87 | gpt-5.4-miniClosedOpenAI · GPT 5.4 · best of 6 rows | 28.1% | Independent | reasoning_effortxhigh | Partially comparable-31.0 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 88 | Qwen3 MaxClosedQwen · Qwen3 · best of 4 rows | 28.0% | Independent | reasoningon | Partially comparable-31.1 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 89 | grok-4.20-0309-non-reasoningClosedxAI · Grok | 27.9% | Independent | group defaults | Partially comparable-31.2 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 90 | GPT-5-CodexClosedOpenAI · GPT 5 · best of 2 rows | 27.9% | Independent | reasoning_efforthigh | Partially comparable-31.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 90 | Qwen3.6 PlusClosedQwen · Qwen3.6 · best of 2 rows | 27.9% | Independent | reasoningon | Partially comparable-31.3 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 92 | GLM 5 TurboClosedZ.ai (Zhipu AI) · GLM5 · best of 2 rows | 27.8% | Independent | reasoningon | Partially comparable-31.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 92 | Hy3 previewOpen weightsTencent | 27.8% | Independent | group defaults | Partially comparable-31.4 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 94 | GLM 4.7Open weightsZ.ai (Zhipu AI) · GLM4.7 · best of 4 rows | 27.4% | Independent | reasoningon | Partially comparable-31.7 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 95 | MiMo-V2.5Open weightsXiaomi · best of 2 rows | 27.2% | Independent | reasoningon | Partially comparable-31.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 96 | grok-4ClosedSpaceXAI · Grok 4 · best of 2 rows | 26.7% | Independent | reasoningon | Partially comparable-32.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 97 | GPT-5.1-CodexClosedOpenAI · GPT 5.1 · best of 2 rows | 25.7% | Independent | reasoning_efforthigh | Partially comparable-33.4 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 98 | Qwen3.5-122B-A10BOpen weightsQwen · Qwen3.5 · best of 4 rows | 25.2% | Independent | reasoningon | Partially comparable-33.9 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 99 | DeepSeek V3Open weightsDeepSeek · DeepSeek · best of 5 rows | 24.6% | Independent | reasoningon | Partially comparable-34.6 pt | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 99 | DeepSeek V3.2Open weightsDeepSeek · DeepSeek-V3 | 24.6% | Independent | group defaults | Partially comparable-34.6 pt | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
One row per canonical model — its best current row inside this comparability group (effort variants are folded into the model). Bars are relative to the page's best score. “vs leader” reads comparability: partially comparable = same task, conditions differ (reasoning effort, temperature, judge). Rules →