| 01 |  Anthropic/Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)released 1mo ago · coding 77 | 59.9 | $20.00 | 72 | 71.29 s | 71.29 s |
| 02 |  OpenAI/GPT-5.6 Sol (max)released 2d ago · coding 77 | 58.9 | $11.25 | 89 | 76.83 s | 76.83 s |
| 03 | OpenAI/GPT-5.6 Sol (xhigh)released 2d ago · coding 78 | 57.7 | $11.25 | 69 | 9.13 s | 9.13 s |
| 04 | OpenAI/GPT-5.6 Sol (high)released 2d ago · coding 77 | 55.9 | $11.25 | 71 | 9.61 s | 9.61 s |
| 05 | Anthropic/Claude Opus 4.8 (Adaptive Reasoning, Max Effort)released 1mo ago · coding 74 | 55.7 | $10.00 | 57 | 30.42 s | 30.42 s |
| 06 | OpenAI/GPT-5.6 Terra (max)released 2d ago · coding 77 | 55.0 | $5.63 | 170 | 67.71 s | 67.71 s |
| 07 | OpenAI/GPT-5.5 (xhigh)released 3mo ago · coding 75 | 54.8 | $11.25 | 64 | 23.27 s | 23.27 s |
| 08 |  SpaceXAI/Grok 4.5 (high)released 3d ago · coding 72 | 53.8 | $3.00 | 109 | 13.09 s | 13.09 s |
| 09 | OpenAI/GPT-5.6 Sol (medium)released 2d ago · coding 76 | 53.6 | $11.25 | 62 | 4.41 s | 4.41 s |
| 10 | Anthropic/Claude Opus 4.7 (Adaptive Reasoning, Max Effort)released 3mo ago · coding 74 | 53.5 | $10.00 | 48 | 17.78 s | 17.78 s |
| 11 | Anthropic/Claude Sonnet 5 (Adaptive Reasoning, Max Effort)released 11d ago · coding 72 | 53.4 | $4.00 | 78 | 105.11 s | 105.11 s |
| 12 | OpenAI/GPT-5.5 (high)released 3mo ago · coding 72 | 53.1 | $11.25 | 62 | 20.00 s | 20.00 s |
| 13 | OpenAI/GPT-5.6 Terra (xhigh)released 2d ago · coding 71 | 51.6 | $5.63 | 131 | 5.92 s | 5.92 s |
| 14 | OpenAI/GPT-5.4 (xhigh)released 4mo ago · coding 71 | 51.4 | $5.63 | 151 | 120.67 s | 120.67 s |
| 15 | OpenAI/GPT-5.6 Luna (max)released 2d ago · coding 71 | 51.2 | $2.25 | 253 | 62.09 s | 62.09 s |
| 16 |  Z AI/GLM-5.2 (max)released 25d ago · coding 69 | 51.1 | $2.15 | 173 | 919 ms | 12.49 s |
| 17 |  Meta/Muse Spark 1.1 (xhigh)released 2d ago · coding 71 | 50.6 | $2.00 | 136 | 775 ms | 15.52 s |
| 18 | OpenAI/GPT-5.5 (medium)released 3mo ago · coding 72 | 50.4 | $11.25 | 60 | 3.23 s | 3.23 s |
| 19 |  Google/Gemini 3.5 Flash (high)released 2mo ago · coding 70 | 50.2 | $3.38 | 237 | 11.02 s | 11.02 s |
| 20 | OpenAI/GPT-5.6 Sol (low)released 2d ago · coding 70 | 49.4 | $11.25 | 75 | 2.16 s | 2.16 s |
| 21 | OpenAI/GPT-5.6 Luna (xhigh)released 2d ago · coding 69 | 49.1 | $2.25 | 220 | 33.24 s | 33.24 s |
| 22 | OpenAI/GPT-5.6 Terra (high)released 2d ago · coding 67 | 49.0 | $5.63 | 117 | 1.65 s | 1.65 s |
| 23 | Anthropic/Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)released 5mo ago · coding 63 | 47.2 | $6.00 | 57 | 70.09 s | 70.09 s |
| 24 | Google/Gemini 3.1 Pro Previewreleased 5mo ago · coding 69 | 46.5 | $4.50 | 131 | 19.75 s | 19.75 s |
| 25 | OpenAI/GPT-5.6 Luna (high)released 2d ago · coding 63 | 46.1 | $2.25 | 214 | 4.96 s | 4.96 s |
| 26 |  Alibaba/Qwen3.7 Maxreleased 2mo ago · coding 66 | 46.0 | $3.75 | 200 | 1.62 s | 13.69 s |
| 27 | OpenAI/GPT-5.6 Terra (medium)released 2d ago · coding 65 | 45.6 | $5.63 | 124 | 1.21 s | 1.21 s |
| 28 | Google/Gemini 3.5 Flash (medium)released 2mo ago | 45.4 | $3.38 | 236 | 9.60 s | 9.60 s |
| 29 |  MiniMax/MiniMax-M3released 1mo ago · coding 59 | 44.4 | $0.525 | 106 | 1.40 s | 20.23 s |
| 30 |  DeepSeek/DeepSeek V4 Pro (Reasoning, Max Effort)released 3mo ago · coding 59 | 44.3 | $0.544 | 61 | 1.05 s | 72.92 s |
| 31 | OpenAI/GPT-5.3 Codex (xhigh)released 5mo ago | 44.3 | $4.81 | 83 | 81.50 s | 81.50 s |
| 32 |  Kimi/Kimi K2.6released 3mo ago · coding 62 | 44.2 | $1.71 | 27 | 1.41 s | 163.88 s |
| 33 | Anthropic/Claude Opus 4.6 (Adaptive Reasoning, Max Effort)released 5mo ago | 43.7 | $10.00 | 47 | 12.33 s | 12.33 s |
| 34 | OpenAI/GPT-5.5 (low)released 3mo ago · coding 61 | 43.5 | $11.25 | 61 | 1.75 s | 1.75 s |
| 35 | Meta/Muse Sparkreleased 3mo ago · coding 59 | 43.1 | Free | — | — | — |
| 36 | Anthropic/Claude Opus 4.7 (Non-reasoning, High Effort)released 3mo ago | 42.7 | $10.00 | 45 | 1.59 s | 1.59 s |
| 37 | OpenAI/GPT-5.2 (xhigh)released 7mo ago · math 99 | 42.2 | $4.81 | 76 | 75.51 s | 75.51 s |
| 38 |  Xiaomi/MiMo-V2.5-Proreleased 3mo ago · coding 60 | 42.2 | $0.544 | 50 | 2.25 s | 42.31 s |
| 39 | Kimi/Kimi K2.7 Codereleased 29d ago · coding 61 | 41.9 | $1.71 | 41 | 1.21 s | 55.85 s |
| 40 | Anthropic/Claude Sonnet 5 (Non-reasoning, High Effort)released 11d ago · coding 66 | 41.7 | $4.00 | 58 | 897 ms | 897 ms |
| 41 | OpenAI/GPT-5.6 Sol (Non-reasoning)released 2d ago · coding 65 | 41.2 | $11.25 | — | — | — |
| 42 | NANex AGI/Nex-N2-Proreleased 1mo ago · coding 59 | 41.0 | $1.00 | 142 | 921 ms | 15.01 s |
| 43 | Anthropic/Claude Opus 4.5 (Reasoning)released 8mo ago · math 91 | 40.8 | $10.00 | 50 | 9.13 s | 9.13 s |
| 44 | DeepSeek/DeepSeek V4 Pro (Reasoning, High Effort)released 3mo ago | 40.8 | $0.544 | 62 | 1.03 s | 33.20 s |
| 45 | OpenAI/GPT-5.6 Terra (low)released 2d ago · coding 58 | 40.5 | $5.63 | 130 | 1.21 s | 1.21 s |
| 46 | DeepSeek/DeepSeek V4 Flash (Reasoning, Max Effort)released 3mo ago · coding 56 | 40.3 | $0.175 | 108 | 862 ms | 52.88 s |
| 47 | Xiaomi/MiMo-V2-Proreleased 4mo ago | 40.3 | $1.50 | — | — | — |
| 48 | Z AI/GLM-5.1 (Reasoning)released 3mo ago · coding 56 | 40.2 | $2.15 | 70 | 900 ms | 55.31 s |
| 49 | OpenAI/GPT-5.2 Codex (xhigh)released 7mo ago | 40.1 | $4.81 | 129 | 1.15 s | 1.15 s |
| 50 | OpenAI/GPT-5.4 mini (xhigh)released 4mo ago · coding 56 | 40.0 | $1.69 | 155 | 4.76 s | 4.76 s |
| 51 | Alibaba/Qwen3.6 Max Previewreleased 3mo ago | 40.0 | $2.92 | 51 | 2.26 s | 41.41 s |
| 52 | SpaceXAI/Grok Build 0.1 0616coding 52 | 39.8 | $1.25 | 53 | 406 ms | 37.92 s |
| 53 | Google/Gemini 3 Pro Preview (high)released 8mo ago · math 96 | 39.6 | $4.50 | — | — | — |
| 54 | Alibaba/Qwen3.6 Plusreleased 3mo ago · coding 55 | 39.6 | $1.13 | 53 | 1.90 s | 107.51 s |
| 55 | Z AI/GLM-5 (Reasoning)released 5mo ago | 39.5 | $1.55 | 46 | 1.14 s | 68.36 s |
| 56 | OpenAI/GPT-5.4 (low)released 4mo ago | 39.1 | $5.63 | 104 | 1.16 s | 1.16 s |
| 57 | Alibaba/Qwen3.7 Plusreleased 1mo ago · coding 56 | 39.0 | $0.700 | 43 | 2.40 s | 49.13 s |
| 58 |  China Mobile/JT-4.1 Flash 236B A21Breleased 2d ago · coding 52 | 38.8 | Free | — | — | — |
| 59 | OpenAI/GPT-5.4 nano (xhigh)released 4mo ago · coding 56 | 38.2 | $0.463 | 160 | 2.54 s | 2.54 s |
| 60 | Z AI/GLM-5-Turboreleased 4mo ago | 38.1 | Free | — | — | — |
| 61 | OpenAI/GPT-5.6 Luna (medium)released 2d ago · coding 51 | 38.1 | $2.25 | 218 | 1.45 s | 1.45 s |
| 62 | Kimi/Kimi K2.5 (Reasoning)released 6mo ago | 38.1 | $1.20 | 39 | 1.22 s | 76.80 s |
| 63 | MiniMax/MiniMax-M2.7released 4mo ago · coding 53 | 38.1 | $0.525 | 50 | 1.42 s | 50.96 s |
| 64 | OpenAI/GPT-5.2 (medium)released 7mo ago · math 97 | 38.0 | $4.81 | — | — | — |
| 65 | Anthropic/Claude Opus 4.6 (Non-reasoning, High Effort)released 5mo ago | 37.8 | $10.00 | 42 | 2.02 s | 2.02 s |
| 66 | Google/Gemini 3 Flash Preview (Reasoning)released 7mo ago · math 97 | 37.8 | $1.13 | 192 | 5.94 s | 5.94 s |
| 67 |  NVIDIA/Nemotron 3 Ultra 550B A55B (Reasoning)released 1mo ago · coding 49 | 37.8 | $1.18 | 171 | 849 ms | 14.18 s |
| 68 | SpaceXAI/Grok 4.3 (high)released 2mo ago · coding 42 | 37.6 | $1.56 | 110 | 36.51 s | 36.51 s |
| 69 | DeepSeek/DeepSeek V4 Flash (Reasoning, High Effort)released 3mo ago | 37.4 | $0.175 | — | — | — |
| 70 | Xiaomi/MiMo-V2.5released 3mo ago · coding 57 | 37.2 | $0.175 | 84 | 1.97 s | 25.85 s |
| 71 | Alibaba/Qwen3.6 27B (Reasoning)released 3mo ago · coding 54 | 37.1 | $1.35 | 60 | 1.47 s | 96.43 s |
| 72 | SpaceXAI/Grok 4.20 0309 v2 (Reasoning)released 3mo ago | 37.0 | $3.00 | 182 | 16.84 s | 16.84 s |
| 73 | OpenAI/GPT-5.1 (high)released 8mo ago · coding 49 · math 94 | 36.9 | $3.44 | 97 | 26.94 s | 26.94 s |
| 74 | SpaceXAI/Grok 4.20 0309 (Reasoning)released 4mo ago | 36.5 | $3.00 | — | — | — |
| 75 | Anthropic/Claude 4.5 Sonnet (Reasoning)released 10mo ago · coding 52 · math 88 | 36.4 | $6.00 | 50 | 7.62 s | 7.62 s |
| 76 | Xiaomi/MiMo-V2-Omni-0327released 4mo ago | 36.4 | $0.800 | — | — | — |
| 77 | OpenAI/GPT-5 Codex (high)released 10mo ago · math 99 | 36.1 | $3.44 | 162 | 6.95 s | 6.95 s |
| 78 | SpaceXAI/Grok 4.3 (medium)released 2mo ago | 36.0 | $1.56 | 104 | 21.05 s | 21.05 s |
| 79 | Anthropic/Claude Sonnet 4.6 (Non-reasoning, High Effort)released 5mo ago | 35.9 | $6.00 | 47 | 1.05 s | 1.05 s |
| 80 | Z AI/GLM-5.1 (Non-reasoning)released 3mo ago | 35.4 | $2.15 | 50 | 1.03 s | 1.03 s |
| 81 | OpenAI/GPT-5.5 (Non-reasoning)released 3mo ago · coding 57 | 35.4 | $11.25 | 59 | 951 ms | 951 ms |
| 82 | SpaceXAI/Grok 4.3 (low)released 2mo ago | 35.4 | $1.56 | 105 | 7.74 s | 7.74 s |
| 83 |  KwaiKAT/KAT Coder Pro V2released 4mo ago | 35.4 | $0.525 | — | — | — |
| 84 | Xiaomi/MiMo-V2-Omnireleased 4mo ago | 35.0 | Free | — | — | — |
| 85 | Google/Gemini 3.5 Flash (minimal)released 2mo ago | 34.9 | $3.38 | 218 | 701 ms | 701 ms |
| 86 | Anthropic/Claude Opus 4.5 (Non-reasoning)released 8mo ago · math 63 | 34.7 | $10.00 | 53 | 1.30 s | 1.30 s |
| 87 | OpenAI/GPT-5 (high)released 11mo ago · coding 38 · math 94 | 34.7 | $3.44 | 87 | 74.17 s | 74.17 s |
| 88 | OpenAI/GPT-5.1 Codex (high)released 8mo ago · math 96 | 34.7 | $3.44 | 185 | 3.56 s | 3.56 s |
| 89 | KwaiKAT/KAT-Coder-Pro V1released 8mo ago · coding 59 · math 95 | 34.6 | $0.525 | 108 | 1.10 s | 1.10 s |
| 90 | Kimi/Kimi K2.6 (Non-reasoning)released 3mo ago | 34.6 | $1.71 | 35 | 1.32 s | 1.32 s |
| 91 | Z AI/GLM 5V Turbo (Reasoning)released 3mo ago | 34.5 | Free | — | — | — |
| 92 | Anthropic/Claude Sonnet 4.6 (Non-reasoning, Low Effort)released 5mo ago | 34.3 | $6.00 | 48 | 1.03 s | 1.03 s |
| 93 | Z AI/GLM-5.2 (Non-reasoning)released 25d ago · coding 47 | 34.1 | $3.16 | 121 | 1.09 s | 1.09 s |
| 94 | OpenAI/GPT-5.6 Terra (Non-reasoning)released 2d ago · coding 52 | 34.0 | $5.63 | 127 | 760 ms | 760 ms |
| 95 | Alibaba/Qwen3.5 27B (Reasoning)released 5mo ago | 33.8 | $0.825 | 84 | 1.39 s | 25.13 s |
| 96 | Anthropic/Claude 4.1 Opus (Reasoning)released 11mo ago · math 80 | 33.7 | $30.00 | 34 | 8.24 s | 8.24 s |
| 97 | Z AI/GLM-4.7 (Reasoning)released 7mo ago · coding 45 · math 95 | 33.7 | $1.00 | 116 | 587 ms | 17.82 s |
| 98 | OpenAI/GPT-5 (medium)released 11mo ago · math 92 | 33.7 | $3.44 | 81 | 40.51 s | 40.51 s |
| 99 | MiniMax/MiniMax-M2.5released 5mo ago | 33.7 | $0.525 | 76 | 1.40 s | 27.76 s |
| 100 | Alibaba/Qwen3.5 397B A17B (Reasoning)released 5mo ago · coding 48 | 33.7 | $1.35 | 54 | 1.80 s | 60.94 s |
| 101 |  Tencent/Hy3-preview (Reasoning)released 3mo ago | 33.6 | $0.200 | 196 | 1.74 s | 11.94 s |
| 102 | OpenAI/GPT-5.5 Instant (May 2026)released 2mo ago | 33.5 | $11.25 | — | — | — |
| 103 | OpenAI/GPT-5.6 Luna (low)released 2d ago · coding 44 | 33.3 | $2.25 | 229 | 1.11 s | 1.11 s |
| 104 | Xiaomi/MiMo-V2-Flash (Feb 2026)released 7mo ago | 33.2 | $0.150 | — | — | — |
| 105 | Google/Gemini 3 Pro Preview (low)released 8mo ago · math 87 | 33.1 | $4.50 | — | — | — |
| 106 | Kimi/Kimi K2 Thinkingreleased 8mo ago · math 95 | 32.7 | $1.07 | 158 | 819 ms | 13.46 s |
| 107 | Z AI/GLM-5 (Non-reasoning)released 5mo ago | 32.4 | $1.55 | 56 | 2.81 s | 2.81 s |
| 108 | Alibaba/Qwen3.5 122B A10B (Reasoning)released 5mo ago · coding 46 | 32.3 | $1.10 | 145 | 1.09 s | 14.89 s |
| 109 | DeepSeek/DeepSeek V3.2 (Reasoning)released 7mo ago · coding 44 · math 92 | 32.0 | $0.315 | — | — | — |
| 110 | Alibaba/Qwen3.5 397B A17B (Non-reasoning)released 5mo ago | 32.0 | $1.35 | 56 | 1.76 s | 1.76 s |
| 111 | Alibaba/Qwen3 Max Thinkingreleased 6mo ago | 31.7 | Free | — | — | — |
| 112 | Alibaba/Qwen3.6 35B A3B (Reasoning)released 3mo ago · coding 42 | 31.6 | $0.557 | 119 | 1.40 s | 46.77 s |
| 113 | MiniMax/MiniMax-M2.1released 7mo ago · math 83 | 31.4 | $0.525 | 77 | 1.18 s | 27.09 s |
| 114 | DeepSeek/DeepSeek V4 Pro (Non-reasoning)released 3mo ago | 31.2 | $0.544 | 62 | 1.05 s | 1.05 s |
| 115 | OpenAI/GPT-5 (low)released 11mo ago · math 83 | 31.2 | $3.44 | 85 | 7.92 s | 7.92 s |
| 116 | Xiaomi/MiMo-V2-Flash (Reasoning)released 7mo ago · math 96 | 31.2 | $0.150 | — | — | — |
| 117 | OpenAI/GPT-5 mini (medium)released 11mo ago · math 85 | 30.9 | $0.688 | 103 | 14.60 s | 14.60 s |
| 118 | OpenAI/GPT-5.1 Codex mini (high)released 8mo ago · math 92 | 30.6 | $0.688 | 212 | 3.33 s | 3.33 s |
| 119 | SpaceXAI/Grok 4.1 Fast (Reasoning)released 8mo ago · math 89 | 30.6 | Free | — | — | — |
| 120 | Alibaba/Qwen3.5 Omni Plusreleased 3mo ago | 30.6 | $1.50 | 57 | 1.25 s | 1.25 s |
| 121 |  InclusionAI/Ring-2.6-1Treleased 2mo ago · coding 43 | 30.6 | $0.850 | 125 | 1.81 s | 17.77 s |
| 122 | Alibaba/Qwen3.6 27B (Non-reasoning)released 3mo ago · coding 47 | 30.5 | $1.35 | 60 | 1.40 s | 1.40 s |
| 123 | DeepSeek/DeepSeek V3.1 Terminus (Reasoning)released 10mo ago · coding 44 · math 90 | 30.4 | $1.91 | — | — | — |
| 124 |  StepFun/Step 3.7 Flashreleased 1mo ago · coding 40 | 30.3 | $0.438 | 401 | 733 ms | 5.71 s |
| 125 | OpenAI/GPT-5.4 nano (medium)released 4mo ago | 30.2 | $0.463 | 168 | 3.37 s | 3.37 s |
| 126 |  Mistral/Mistral Medium 3.5released 2mo ago · coding 47 | 29.9 | $3.00 | 92 | 761 ms | 22.48 s |
| 127 | OpenAI/GPT-5.4 mini (medium)released 4mo ago | 29.8 | $1.69 | 171 | 4.82 s | 4.82 s |
| 128 | Anthropic/Claude 4.5 Haiku (Reasoning)released 9mo ago · coding 44 · math 84 | 29.6 | $2.00 | 119 | 11.96 s | 11.96 s |
| 129 | Google/Gemma 4 31B (Reasoning)released 3mo ago · coding 43 | 29.4 | Free | 36 | 934 ms | 49.68 s |
| 130 | Kimi/Kimi K2.5 (Non-reasoning)released 6mo ago | 29.4 | $1.20 | 42 | 1.18 s | 1.18 s |
| 131 | Anthropic/Claude 4.5 Sonnet (Non-reasoning)released 10mo ago · math 37 | 29.3 | $6.00 | 46 | 1.48 s | 1.48 s |
| 132 | Alibaba/Qwen3.5 27B (Non-reasoning)released 5mo ago | 29.3 | $0.825 | 93 | 1.44 s | 1.44 s |
| 133 | Alibaba/Qwen3.5 35B A3B (Reasoning)released 5mo ago | 29.3 | $0.688 | 166 | 1.24 s | 13.25 s |
| 134 | OpenAI/GPT-5.5 Instant (June 2026)released 16d ago · coding 39 | 28.9 | $11.25 | — | — | — |
| 135 | DeepSeek/DeepSeek V4 Flash (Non-reasoning)released 3mo ago | 28.7 | $0.175 | 105 | 906 ms | 906 ms |
| 136 | Z AI/GLM-4.6 (Reasoning)released 9mo ago · coding 46 · math 86 | 28.7 | $0.963 | 46 | 1.21 s | 45.07 s |
| 137 | China Mobile/JT-35B-Flashreleased 2mo ago | 28.4 | Free | — | — | — |
| 138 | MiniMax/MiniMax-M2released 9mo ago · math 78 | 28.3 | $0.525 | 77 | 1.22 s | 27.35 s |
| 139 | Anthropic/Claude 4.1 Opus (Non-reasoning)released 11mo ago | 28.2 | $30.00 | 36 | 2.03 s | 2.03 s |
| 140 | Xiaomi/MiMo-V2.5-Pro (Non-reasoning)released 3mo ago | 27.9 | $0.926 | 63 | 1.34 s | 1.34 s |
| 141 | OpenAI/GPT-5.4 (Non-reasoning)released 4mo ago | 27.7 | $5.63 | 104 | 680 ms | 680 ms |
| 142 | Alibaba/Qwen3.5 122B A10B (Non-reasoning)released 5mo ago · coding 43 | 27.6 | $1.10 | 164 | 1.09 s | 1.09 s |
| 143 | Google/Gemini 3 Flash Preview (Non-reasoning)released 7mo ago · math 56 | 27.4 | $1.13 | 194 | 719 ms | 719 ms |
| 144 | SpaceXAI/Grok 4 Fast (Reasoning)released 10mo ago · math 90 | 27.4 | $0.275 | — | — | — |
| 145 | Z AI/GLM-4.7 (Non-reasoning)released 7mo ago · math 48 | 26.6 | $1.00 | 116 | 630 ms | 630 ms |
| 146 | OpenAI/GPT-5.6 Luna (Non-reasoning)released 2d ago · coding 39 | 26.6 | $2.25 | 219 | 579 ms | 579 ms |
| 147 | Tencent/Hy3-preview (Non-reasoning)released 3mo ago | 26.1 | $0.200 | 183 | 1.67 s | 1.67 s |
| 148 | InclusionAI/Ling-2.6-1Treleased 3mo ago | 26.1 | $0.850 | — | — | — |
| 149 |  ByteDance Seed/Doubao Seed Codereleased 8mo ago · math 79 | 26.0 | Free | — | — | — |
| 150 | OpenAI/GPT-5.2 (Non-reasoning)released 7mo ago · math 51 | 26.0 | $4.81 | 69 | 718 ms | 718 ms |
| 151 | StepFun/Step 3.5 Flash 2603released 3mo ago | 26.0 | $0.150 | 196 | 889 ms | 11.12 s |
| 152 | Google/Gemma 4 26B A4B (Reasoning)released 3mo ago · coding 39 | 25.7 | $0.198 | — | — | — |
| 153 | StepFun/Step 3.5 Flashreleased 5mo ago | 25.5 | $0.150 | 194 | 811 ms | 11.12 s |
| 154 | DeepSeek/DeepSeek V3.2 Exp (Reasoning)released 10mo ago · math 88 | 25.4 | $0.315 | — | — | — |
| 155 | NVIDIA/NVIDIA Nemotron 3 Super 120B A12B (Reasoning)released 4mo ago · coding 38 | 25.4 | $0.381 | 146 | 933 ms | 14.64 s |
| 156 | OpenAI/GPT-5 mini (high)released 11mo ago · coding 16 · math 91 | 25.3 | $0.688 | 90 | 84.47 s | 84.47 s |
| 157 |  Inception/Mercury 2released 5mo ago | 25.3 | $0.375 | 1042 | 4.10 s | 4.10 s |
| 158 | Google/Gemini 3.1 Flash-Litereleased 4mo ago · coding 35 | 25.0 | $0.563 | 309 | 5.36 s | 5.36 s |
| 159 | Alibaba/Qwen3 Max Thinking (Preview)released 8mo ago · math 82 | 25.0 | $2.40 | 60 | 2.00 s | 35.07 s |
| 160 | SpaceXAI/Grok 4.3 (Non-reasoning)released 2mo ago · coding 35 | 24.8 | $1.56 | 89 | 653 ms | 653 ms |
| 161 | DeepSeek/DeepSeek V3.2 (Non-reasoning)released 7mo ago · math 59 | 24.7 | $0.315 | — | — | — |
| 162 |  LG AI Research/K-EXAONE (Reasoning)released 6mo ago · math 90 | 24.7 | Free | — | — | — |
| 163 | Xiaomi/MiMo-V2-Flash (Non-reasoning)released 7mo ago · coding 50 · math 68 | 24.7 | $0.150 | — | — | — |
| 164 |  Arcee AI/Trinity Large Thinkingreleased 3mo ago | 24.5 | $0.395 | 212 | 707 ms | 10.13 s |
| 165 | Alibaba/Qwen3.6 35B A3B (Non-reasoning)released 3mo ago | 24.2 | $0.844 | 124 | 1.34 s | 1.34 s |
| 166 | Alibaba/Qwen3 Maxreleased 10mo ago · math 81 | 24.0 | $2.40 | 50 | 1.98 s | 1.98 s |
| 167 | Google/Gemini 2.5 Flash Preview (Sep '25) (Reasoning)released 10mo ago · math 78 | 23.8 | Free | — | — | — |
| 168 | OpenAI/gpt-oss-120b (high)released 11mo ago · coding 30 · math 93 | 23.8 | $0.262 | 294 | 515 ms | 7.33 s |
| 169 | Anthropic/Claude 4.5 Haiku (Non-reasoning)released 9mo ago · math 39 | 23.7 | $2.00 | 97 | 781 ms | 781 ms |
| 170 | Kimi/Kimi K2 0905released 10mo ago · math 57 | 23.5 | $1.07 | 36 | 1.06 s | 1.06 s |
| 171 | Alibaba/Qwen3.5 35B A3B (Non-reasoning)released 5mo ago | 23.4 | $0.688 | 196 | 1.29 s | 1.29 s |
| 172 | LG AI Research/EXAONE 4.5 33Breleased 3mo ago | 23.0 | Free | — | — | — |
| 173 | Z AI/GLM-4.6 (Non-reasoning)released 9mo ago · math 44 | 23.0 | $0.981 | 40 | 2.11 s | 2.11 s |
| 174 | Z AI/GLM-4.7-Flash (Reasoning)released 6mo ago | 22.9 | $0.153 | 92 | 920 ms | 22.58 s |
| 175 |  Cohere/Command A+released 2mo ago · coding 28 | 22.5 | Free | 142 | 190 ms | 14.28 s |
| 176 | SpaceXAI/Grok 4.20 0309 (Non-reasoning)released 4mo ago | 22.5 | $3.00 | — | — | — |
| 177 | DeepSeek/DeepSeek V3.2 Specialereleased 7mo ago · math 97 | 22.2 | Free | — | — | — |
| 178 | Google/Gemma 4 12B (Reasoning)released 1mo ago | 22.0 | $0.150 | 49 | 1.47 s | 42.24 s |
| 179 |  Baidu/ERNIE 5.0 Thinking Previewreleased 8mo ago · math 85 | 21.9 | Free | — | — | — |
| 180 | Google/Gemma 4 31B (Non-reasoning)released 3mo ago · coding 33 | 21.8 | $0.205 | 68 | 677 ms | 677 ms |
| 181 | SpaceXAI/Grok 4.20 0309 v2 (Non-reasoning)released 3mo ago | 21.8 | $3.00 | 147 | 440 ms | 440 ms |
| 182 |  Amazon/Nova 2.0 Pro Preview (medium)released 8mo ago · coding 34 · math 89 | 21.8 | $3.44 | 121 | 15.70 s | 32.28 s |
| 183 | SpaceXAI/Grok Code Fast 1released 11mo ago · math 43 | 21.6 | Free | — | — | — |
| 184 | DeepSeek/DeepSeek V3.1 Terminus (Non-reasoning)released 10mo ago · math 54 | 21.4 | $0.453 | — | — | — |
| 185 | Alibaba/Qwen3.5 9B (Reasoning)released 4mo ago · coding 29 | 21.4 | $0.113 | 59 | 1.26 s | 34.88 s |
vicrodh/qbzjust droppedNEW
kowalski-ptr/compass-before-compactjust droppedNEW
lastmile-ai/mcp-agentjust droppedREPO
Dicklesworthstone/destructive_command_guard+552 stars 24hREPO
obra/superpowers+211 stars 24hREPO
diegosouzapw/OmniRoute+194 stars 24hREPO
addyosmani/agent-skills+182 stars 24hREPO
Zackriya-Solutions/meetily+152 stars 24hNEW