1 Claude Fable 5.1 Closed Anthropic · Claude · best of 10 rows 53.4 Independent reasoning_effort max version 4.3 leader obs. 12 Sept 2026 artificialanalysis.ai T2 History 2 gpt-6-astra Closed OpenAI · GPT 6 · best of 11 rows 52.8 Independent reasoning_effort max version 4.3 Comparable -0.56 obs. 12 Sept 2026 artificialanalysis.ai T2 History 3 Claude Opus 5 Closed Anthropic · Claude · best of 10 rows 50.7 Independent reasoning_effort max version 4.3 Comparable -2.67 obs. 12 Sept 2026 artificialanalysis.ai T2 History 4 Claude Fable 5 Closed Anthropic · Claude · best of 2 rows 49.7 Independent reasoning on version 4.3 Partially comparable -3.67 obs. 12 Sept 2026 artificialanalysis.ai T2 History 5 Muse Spark 1.3 Closed Meta AI · best of 4 rows 48.2 Independent reasoning_effort max version 4.3 Comparable -5.20 obs. 12 Sept 2026 artificialanalysis.ai T2 History 6 gpt-5.6-sol Closed OpenAI · GPT 5.6 · best of 12 rows 47.1 Independent reasoning_effort max version 4.3 Comparable -6.31 obs. 12 Sept 2026 artificialanalysis.ai T2 History 7 GLM 5.3 Open weights Z.ai (Zhipu AI) · GLM5.3 · best of 2 rows 44.9 Independent reasoning_effort max version 4.3 Comparable -8.51 obs. 12 Sept 2026 artificialanalysis.ai T2 History 8 Grok 4.6 Closed xAI · Grok · best of 8 rows 44.4 Independent reasoning_effort high version 4.3 Partially comparable -8.96 obs. 12 Sept 2026 artificialanalysis.ai T2 History 9 Kimi K3 Open weights Moonshot AI · Kimi · best of 4 rows 43.8 Independent reasoning_effort max version 4.3 Comparable -9.59 obs. 12 Sept 2026 artificialanalysis.ai T2 History 10 gpt-5.6-terra Closed OpenAI · GPT 5.6 · best of 12 rows 42.3 Independent reasoning_effort max version 4.3 Comparable -11.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 11 Claude Opus 4.8 Closed Anthropic · Claude · best of 2 rows 42.0 Independent reasoning_effort max version 4.3 Comparable -11.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 12 GLM 5.3 Flash Open weights Z.ai (Zhipu AI) · GLM5.3 · best of 2 rows 41.9 Independent reasoning on version 4.3 Partially comparable -11.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 13 Gemini 3.8 Flash Closed Google · Gemini 3.8 · best of 6 rows 41.2 Independent reasoning_effort high version 4.3 Partially comparable -12.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 14 Claude Opus 4.7 Closed Anthropic · Claude · best of 4 rows 40.7 Independent reasoning_effort max version 4.3 Comparable -12.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 15 Qwen 3.8 Max Closed Qwen · Qwen3.8 · best of 2 rows 40.3 Independent reasoning on version 4.3 Partially comparable -13.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 16 Qwen3.8 2.4T A95B Open weights Qwen · Qwen3.8 · best of 2 rows 40.0 Independent reasoning on version 4.3 Partially comparable -13.3 obs. 12 Sept 2026 artificialanalysis.ai T2 History 17 Qwen3.8 Flash Open weights Qwen · Qwen3.8 · best of 2 rows 39.9 Independent reasoning on version 4.3 Partially comparable -13.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 18 Muse Spark 1.2 Closed Meta AI · best of 2 rows 39.8 Independent reasoning_effort xhigh version 4.3 Partially comparable -13.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 19 Gemini 3.7 Flash Closed Google · Gemini 3.7 · best of 6 rows 39.6 Independent reasoning_effort medium version 4.3 Partially comparable -13.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 20 DeepSeek-V4.1-Flash Open weights DeepSeek · DeepSeek · best of 2 rows 39.5 Independent reasoning_effort max version 4.3 Comparable -13.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 21 Grok 4.5 Closed xAI · Grok · best of 2 rows 39.1 Independent reasoning_effort high version 4.3 Partially comparable -14.3 obs. 12 Sept 2026 artificialanalysis.ai T2 History 22 gpt-5.4 Closed OpenAI · GPT 5.4 · best of 6 rows 39.0 Independent reasoning_effort xhigh version 4.3 Partially comparable -14.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 23 Z.ai GLM 5.2 Open weights Z.ai (Zhipu AI) · GLM5.2 · best of 4 rows 38.6 Independent reasoning_effort max version 4.3 Comparable -14.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 24 gpt-5.5 Closed OpenAI · GPT 5.5 · best of 10 rows 38.6 Independent reasoning_effort xhigh version 4.3 Partially comparable -14.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 25 Claude Sonnet 5 Closed Anthropic · Claude · best of 12 rows 38.4 Independent reasoning_effort max version 4.3 Comparable -15.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 26 gpt-5.6-luna Closed OpenAI · GPT 5.6 · best of 12 rows 37.5 Independent reasoning_effort max version 4.3 Comparable -15.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 27 deepseek-v4-pro Closed DeepSeek · V4 · best of 2 rows 36.3 Independent reasoning_effort max version 4.3 Comparable -17.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 28 agnes-3-0-flash Closed Sapiens AI · best of 2 rows 35.5 Independent reasoning on version 4.3 Partially comparable -17.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 29 agnes-2-5-pro-beta Closed Sapiens AI · best of 2 rows 35.2 Independent reasoning on version 4.3 Partially comparable -18.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 30 deepseek-v4-flash-vision Closed DeepSeek · DeepSeek · best of 2 rows 35.0 Independent reasoning_effort max version 4.3 Comparable -18.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 31 deepseek-v4-flash Open weights DeepSeek · DeepSeek · best of 2 rows 34.5 Independent reasoning_effort max version 4.3 Comparable -18.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 32 Gemini 3.6 Flash Closed Google · Gemini 3.6 · best of 2 rows 34.3 Independent reasoning on version 4.3 Partially comparable -19.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 33 Muse Spark 1.1 Closed Meta AI · best of 2 rows 34.3 Independent reasoning_effort xhigh version 4.3 Partially comparable -19.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 34 Qwen3.8 27B Open weights Qwen · Qwen3.8 · best of 8 rows 33.9 Independent reasoning_effort xhigh version 4.3 Partially comparable -19.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 35 Gemini 3.5 Flash Closed Google · Gemini 3.5 · best of 6 rows 33.6 Independent reasoning_effort medium version 4.3 Partially comparable -19.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 36 motif-3 Open weights Motif Technologies · best of 2 rows 33.6 Independent reasoning on version 4.3 Partially comparable -19.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 37 gpt-5.3-codex Closed OpenAI · GPT 5.3 · best of 2 rows 32.5 Independent reasoning_effort xhigh version 4.3 Partially comparable -20.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 38 motif-0714 Closed Motif Technologies · best of 2 rows 32.3 Independent reasoning on version 4.3 Partially comparable -21.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 39 Claude Opus 4.6 Closed Anthropic · Claude · best of 4 rows 31.9 Independent reasoning adaptive reasoning_effort max version 4.3 Partially comparable -21.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 40 Kimi K2.6 Open weights Moonshot AI · Kimi · best of 4 rows 31.3 Independent reasoning on version 4.3 Partially comparable -22.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 41 muse-spark Closed Meta AI · best of 2 rows 31.3 Independent reasoning on version 4.3 Partially comparable -22.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 42 deepseek-v4-pro-0424 Open weights DeepSeek · DeepSeek · best of 4 rows 30.9 Independent reasoning_effort max version 4.3 Comparable -22.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 43 k2-horizon-375b-a23b Open weights MBZUAI Institute of Foundation Models · best of 2 rows 30.7 Independent reasoning on version 4.3 Partially comparable -22.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 44 Claude Sonnet 4.6 Closed Anthropic · Claude · best of 5 rows 30.4 Independent reasoning adaptive reasoning_effort max version 4.3 Partially comparable -22.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 44 gpt-5.2 Closed OpenAI · GPT 5.2 · best of 6 rows 30.4 Independent reasoning_effort xhigh version 4.3 Partially comparable -22.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 46 apodex-1-1 Closed Apodex · best of 2 rows 30.4 Independent reasoning on version 4.3 Partially comparable -23.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 47 Gemini 3.1 Pro Preview Closed Google · Gemini 3.1 · best of 2 rows 30.4 Independent reasoning on version 4.3 Partially comparable -23.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 48 deepseek-v4-pro-0424-high Open weights DeepSeek · DeepSeek 30.1 Independent version 4.3 Partially comparable -23.3 obs. 11 Sept 2026 artificialanalysis.ai T2 History 49 Qwen3.7 Max Closed Qwen · Qwen3.7 · best of 2 rows 29.9 Independent reasoning on version 4.3 Partially comparable -23.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 50 MiniMax-M3 Open weights MiniMax · MiniMax · best of 2 rows 29.6 Independent reasoning on version 4.3 Partially comparable -23.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 51 Claude Opus 4.5 Closed Anthropic · Claude · best of 4 rows 29.1 Independent reasoning on version 4.3 Partially comparable -24.3 obs. 12 Sept 2026 artificialanalysis.ai T2 History 52 mimo-v2-pro Closed Xiaomi · best of 2 rows 28.6 Independent reasoning on version 4.3 Partially comparable -24.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 53 GPT-5.2-Codex Closed OpenAI · GPT 5.2 · best of 2 rows 28.5 Independent reasoning_effort xhigh version 4.3 Partially comparable -24.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 54 Qwen3.6 Max Preview Closed Qwen · Qwen3.6 · best of 2 rows 28.4 Independent reasoning on version 4.3 Partially comparable -25.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 55 nex-n2-pro Open weights Nex AGI · best of 2 rows 28.2 Independent reasoning on version 4.3 Partially comparable -25.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 56 Solar Pro 4 Closed Upstage · Solar · best of 2 rows 28.1 Independent reasoning on version 4.3 Partially comparable -25.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 57 gemini-3-pro Closed Google · Gemini 3 · best of 4 rows 28.0 Independent reasoning_effort high version 4.3 Partially comparable -25.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 58 GLM 5 Open weights Z.ai (Zhipu AI) · GLM5 · best of 4 rows 27.9 Independent reasoning on version 4.3 Partially comparable -25.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 59 agnes-2-5-pro-alpha Open weights Sapiens AI · best of 2 rows 27.8 Independent reasoning on version 4.3 Partially comparable -25.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 60 jt-4-1-flash-236b-a21b Closed China Mobile · best of 2 rows 27.3 Independent reasoning off version 4.3 Partially comparable -26.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 61 grok-build-0-1-06-16 Closed SpaceXAI · Grok · best of 2 rows 27.2 Independent reasoning on version 4.3 Partially comparable -26.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 62 quasar-438b Closed Multiverse Computing · best of 2 rows 27.1 Independent reasoning_effort max version 4.3 Comparable -26.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 63 Qwen3.6 Plus Closed Qwen · Qwen3.6 · best of 2 rows 27.0 Independent reasoning on version 4.3 Partially comparable -26.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 64 gpt-5-5-instant-06-26 Closed OpenAI · GPT 5.5 · best of 2 rows 26.8 Independent reasoning on version 4.3 Partially comparable -26.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 65 GLM 5 Turbo Closed Z.ai (Zhipu AI) · GLM5 · best of 2 rows 26.6 Independent reasoning on version 4.3 Partially comparable -26.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 66 GLM 5.1 Open weights Z.ai (Zhipu AI) · GLM5.1 · best of 4 rows 26.4 Independent reasoning on version 4.3 Partially comparable -26.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 67 MiMo-V2.5-Pro Open weights Xiaomi · best of 4 rows 26.4 Independent reasoning on version 4.3 Partially comparable -27.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 68 Gemini 3 Flash Preview Closed Google · Gemini 3 26.3 Independent version 4.3 Partially comparable -27.0 obs. 11 Sept 2026 artificialanalysis.ai T2 History 68 gemini-3-flash Closed Google · Gemini 3 · best of 3 rows 26.3 Independent reasoning on version 4.3 Partially comparable -27.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 70 Kimi K2.7 Code Open weights Moonshot AI · Kimi · best of 2 rows 26.3 Independent reasoning on version 4.3 Partially comparable -27.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 71 Inkling Small Open weights Thinking Machines · best of 2 rows 26.1 Independent reasoning on version 4.3 Partially comparable -27.3 obs. 12 Sept 2026 artificialanalysis.ai T2 History 72 Qwen 3.7 Plus Closed Qwen · Qwen3.7 · best of 2 rows 25.8 Independent reasoning on version 4.3 Partially comparable -27.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 73 Hy3 Open weights Tencent · best of 5 rows 25.8 Independent reasoning on version 4.3 Partially comparable -27.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 74 Grok 4.20 Closed xAI · Grok · best of 3 rows 25.7 Independent reasoning on version 4.3 Partially comparable -27.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 75 Inkling Open weights Thinking Machines · best of 2 rows 25.5 Independent reasoning on version 4.3 Partially comparable -27.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 76 Grok 4.3 Closed xAI · Grok · best of 8 rows 25.4 Independent reasoning_effort high version 4.3 Partially comparable -28.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 77 grok-4-20-0309 Closed SpaceXAI · Grok 4.20 · best of 4 rows 25.2 Independent reasoning on version 4.3 Partially comparable -28.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 78 mimo-v2-omni-0327 Closed Xiaomi · best of 2 rows 25.1 Independent reasoning on version 4.3 Partially comparable -28.2 obs. 12 Sept 2026 artificialanalysis.ai T2 History 79 Ling 3.0 Flash Open weights inclusionAI · best of 2 rows 24.9 Independent reasoning on version 4.3 Partially comparable -28.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 80 GPT-5-Codex Closed OpenAI · GPT 5 · best of 2 rows 24.9 Independent reasoning_effort high version 4.3 Partially comparable -28.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 81 deepseek-v4-flash-0420 Open weights DeepSeek · DeepSeek · best of 4 rows 24.8 Independent reasoning_effort high version 4.3 Partially comparable -28.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 81 deepseek-v4-flash-0420-high Open weights DeepSeek · DeepSeek 24.8 Independent version 4.3 Partially comparable -28.5 obs. 11 Sept 2026 artificialanalysis.ai T2 History 83 Ling 3.0 Flash VL Open weights inclusionAI · best of 2 rows 24.8 Independent reasoning on version 4.3 Partially comparable -28.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 84 gpt-5.1 Closed OpenAI · GPT 5.1 · best of 4 rows 24.7 Independent reasoning_effort high version 4.3 Partially comparable -28.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 84 solar-open2-250b Open weights Upstage · Solar · best of 2 rows 24.7 Independent reasoning on version 4.3 Partially comparable -28.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 86 gpt-5.4-mini Closed OpenAI · GPT 5.4 · best of 6 rows 24.6 Independent reasoning_effort xhigh version 4.3 Partially comparable -28.8 obs. 12 Sept 2026 artificialanalysis.ai T2 History 87 mimo-v2-omni Closed Xiaomi · best of 2 rows 23.9 Independent reasoning on version 4.3 Partially comparable -29.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 88 GPT-5.1-Codex Closed OpenAI · GPT 5.1 · best of 2 rows 23.7 Independent reasoning_effort high version 4.3 Partially comparable -29.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 89 GLM 5V Turbo Closed Z.ai (Zhipu AI) · GLM5 · best of 2 rows 23.5 Independent reasoning on version 4.3 Partially comparable -29.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 90 Kimi K2.5 Open weights Moonshot AI · Kimi · best of 4 rows 23.5 Independent reasoning on version 4.3 Partially comparable -29.9 obs. 12 Sept 2026 artificialanalysis.ai T2 History 91 Nemotron 3 Ultra Open weights NVIDIA · Nemotron 3 · best of 2 rows 23.4 Independent reasoning on version 4.3 Partially comparable -30.0 obs. 12 Sept 2026 artificialanalysis.ai T2 History 92 MiniMax M2.7 Open weights MiniMax · MiniMax · best of 2 rows 23.2 Independent reasoning on version 4.3 Partially comparable -30.1 obs. 12 Sept 2026 artificialanalysis.ai T2 History 93 gpt-5 Closed OpenAI · GPT 5 · best of 8 rows 23.0 Independent reasoning_effort high version 4.3 Partially comparable -30.4 obs. 12 Sept 2026 artificialanalysis.ai T2 History 94 Qwen3.5-27B Open weights Qwen · Qwen3.5 · best of 4 rows 22.9 Independent reasoning on version 4.3 Partially comparable -30.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 95 Claude Opus 4.1 Closed Anthropic · Claude · best of 4 rows 22.9 Independent reasoning on version 4.3 Partially comparable -30.5 obs. 12 Sept 2026 artificialanalysis.ai T2 History 96 MiniMax M2.5 Open weights MiniMax · MiniMax · best of 2 rows 22.8 Independent reasoning on version 4.3 Partially comparable -30.6 obs. 12 Sept 2026 artificialanalysis.ai T2 History 97 Hy3 preview Open weights Tencent 22.7 Independent version 4.3 Partially comparable -30.6 obs. 11 Sept 2026 artificialanalysis.ai T2 History 98 a-x-k2 Open weights SK Telecom · best of 2 rows 22.7 Independent reasoning on version 4.3 Partially comparable -30.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 99 gpt-5-5-instant-05-26 Closed OpenAI · GPT 5.5 · best of 2 rows 22.7 Independent reasoning on version 4.3 Partially comparable -30.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History 100 Gemini 3.5 Flash-Lite Closed Google · Gemini 3.5 · best of 2 rows 22.7 Independent reasoning on version 4.3 Partially comparable -30.7 obs. 12 Sept 2026 artificialanalysis.ai T2 History