| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Qwen3.8 Max Preview | Alibaba | 51.3 | 1 | 2026-08-06 |
| 2 | Grok 4.6 | SpaceXAI | 50.7 | 4 | 2026-08-22 |
| 3 | GLM-5.3 | Z.ai | 50.3 | 1 | 2026-08-19 |
| 4 | Qwen3.8 2.4T A95B | Alibaba | 49.1 | 1 | 2026-08-14 |
| 5 | Qwen3.8 27B | Alibaba | 48 | 4 | 2026-08-22 |
| 6 | Kimi K3 | Moonshot | 46 | 3 | 2026-07-31 |
| 7 | Opus 5 | Anthropic | 44.7 | 5 | 2026-07-25 |
| 8 | GPT-5.6 Sol | OpenAI | 44.3 | 6 | 2026-07-10 |
| 9 | Grok4.5 | SpaceXAI | 42.1 | 1 | 2026-07-09 |
| 10 | GPT-5.6 Terra | OpenAI | 40.2 | 6 | 2026-07-10 |
| 11 | GPT-5.4 | OpenAI | 39.6 | 1 | 2026-07-03 |
| 12 | DeepSeek-V4-Flash | DeepSeek | 39.4 | 4 | 2026-08-01 |
| 13 | GPT-5.5 | OpenAI | 39 | 5 | 2026-07-03 |
| 14 | Claude Fable 5 | Anthropic | 38.1 | 1 | 2026-07-03 |
| 15 | Claude Sonnet 5 | Anthropic | 37.3 | 2 | 2026-07-03 |
| 16 | Gemini 3.7 Flash | 35.5 | 3 | 2026-08-14 | |
| 17 | Motif-3 | Motif Technologies | 35.3 | 1 | 2026-08-13 |
| 18 | Muse Spark 1.2 | Meta | 34.8 | 1 | 2026-08-06 |
| 19 | Claude Opus 4.7 | Anthropic | 34.6 | 1 | 2026-07-03 |
| 20 | GLM-5.2 Full Open Source | Z.ai | 34.6 | 2 | 2026-07-11 |
| 21 | Claude Sonnet 4.6 | Anthropic | 34.4 | 1 | 2026-07-03 |
| 22 | Claude Opus 4.8 | Anthropic | 34.2 | 1 | 2026-07-03 |
| 23 | Gemini 3.5 Flash | 32.2 | 1 | 2026-07-03 | |
| 24 | Muse Spark 1.1 | Meta | 31.8 | 1 | 2026-07-11 |
| 25 | GPT-5.6 Luna | OpenAI | 31.1 | 6 | 2026-07-10 |
| 26 | DeepSeek-V4-Pro | DeepSeek | 30.1 | 2 | 2026-07-21 |
| 27 | Gemini 3.6 Flash | 29.9 | 1 | 2026-07-22 | |
| 28 | Inkling | Thinking Machines | 29.1 | 1 | 2026-07-16 |
| 29 | Motif-3-Beta | Motif Technologies | 28.9 | 1 | 2026-07-21 |
| 30 | JT-4.1 Flash 236B A21B | China Mobile | 28 | 1 | 2026-07-10 |
| 31 | GPT-5.4 nano | OpenAI | 27.4 | 1 | 2026-07-03 |
| 32 | Ling-3.0-flash | InclusionAI | 27.2 | 1 | 2026-08-06 |
| 33 | GPT-5.4 mini | OpenAI | 25.6 | 1 | 2026-07-03 |
| 34 | Claude Sonnet 4.5 | Anthropic | 24.5 | 1 | 2026-07-03 |
| 35 | Muse Glimmer | Meta | 23.5 | 1 | 2026-08-11 |
| 36 | Solar Pro4 | Upstage | 23.3 | 1 | 2026-08-13 |
| 37 | Kimi K2.6 | Moonshot | 23.3 | 2 | 2026-07-07 |
| 38 | Hy3-preview | Tencent | 22.9 | 1 | 2026-07-14 |
| 39 | GPT-5 | OpenAI | 22.1 | 1 | 2026-07-05 |
| 40 | G9v3-39A5B | AI9Stars | 22.1 | 1 | 2026-08-04 |
| 41 | Solar Open2 250B | Upstage | 21.6 | 1 | 2026-08-13 |
| 42 | Gemini 3.1 Pro | 21.4 | 2 | 2026-07-07 | |
| 43 | DeepSeek-V3.1-Terminus | DeepSeek | 21 | 1 | 2026-07-09 |
| 44 | Gemini 3 Flash Preview | 20.8 | 1 | 2026-07-03 | |
| 45 | Ling 3.0 Tiny | InclusionAI | 20.8 | 1 | 2026-08-08 |
| 46 | Qwen3.6 Plus | Alibaba | 20.8 | 2 | 2026-07-07 |
| 47 | Kimi K2.7 Code | Moonshot | 20.2 | 2 | 2026-07-07 |
| 48 | Muse Spark | Meta | 19.6 | 2 | 2026-07-07 |
| 49 | Inkling-Small | Thinking Machines | 18.8 | 1 | 2026-07-31 |
| 50 | DeepSeek-V3.2 | DeepSeek | 18.8 | 1 | 2026-07-09 |
| 51 | Qwen3.7 Plus Preview | Alibaba | 17.9 | 2 | 2026-07-07 |
| 52 | Gemini 3.5 Flash Lite | 17.5 | 1 | 2026-07-22 | |
| 53 | Nex-N2-Pro | Nex AGI | 17.5 | 2 | 2026-07-07 |
| 54 | Claude Sonnet 4 | Anthropic | 16.7 | 1 | 2026-07-03 |
| 55 | Qwen3.6 27B | Alibaba | 16.7 | 2 | 2026-07-03 |
| 56 | A.X-K2 | SK Telecom | 16.1 | 1 | 2026-08-13 |
| 57 | GPT-5.1 | OpenAI | 15.9 | 1 | 2026-07-03 |
| 58 | GPT-5 mini | OpenAI | 15.5 | 1 | 2026-07-03 |
| 59 | MiniMax M3 | MiniMax | 15.3 | 2 | 2026-07-07 |
| 60 | Qwen3.5 122B A10B | Alibaba | 15.3 | 2 | 2026-07-09 |
| 61 | Gemma 4 31B | 14.8 | 2 | 2026-07-11 | |
| 62 | K-EXAONE | LG AI | 14.2 | 1 | 2026-07-25 |
| 63 | Kimi K2.5 | Moonshot | 14.2 | 1 | 2026-07-14 |
| 64 | Nemotron 3 Ultra 550B A55B | NVIDIA | 14.2 | 1 | 2026-07-03 |
| 65 | GLM-5.1 | Z.ai | 13.6 | 1 | 2026-07-03 |
| 66 | GLM-4.6 | Z.ai | 13.4 | 1 | 2026-07-03 |
| 67 | Qwen3.5 397B A17B | Alibaba | 13.4 | 1 | 2026-07-03 |
| 68 | Grok Build 0.1 | SpaceXAI | 13.4 | 2 | 2026-07-07 |
| 69 | LongCat-2.0 | Meituan | 13.2 | 1 | 2026-07-20 |
| 70 | GPT OSS 120B | OpenAI | 12.8 | 2 | 2026-07-14 |
| 71 | Agnes 2.5 Pro Alpha | Sapiens AI | 12.4 | 1 | 2026-07-25 |
| 72 | Grok 4.3 | SpaceXAI | 12.4 | 2 | 2026-07-03 |
| 73 | GLM-4.7 | Z.ai | 12.2 | 1 | 2026-07-03 |
| 74 | Step 3.7 Flash | StepFun | 12 | 2 | 2026-07-07 |
| 75 | Gemma 4 26B A4B | 12 | 1 | 2026-07-03 | |
| 76 | Qwen3.7 Max | Alibaba | 11.8 | 1 | 2026-07-03 |
| 77 | GPT-5.5 Instant | OpenAI | 11.8 | 2 | 2026-07-07 |
| 78 | K-EXAONE 2.0 0803 | LG AI | 11.5 | 1 | 2026-08-13 |
| 79 | GPT-5.2 | OpenAI | 11.1 | 1 | 2026-07-03 |
| 80 | EXAONE 4.5 33B | LG AI | 11.1 | 1 | 2026-07-25 |
| 81 | Devstral Small 2 | Mistral | 10.7 | 2 | 2026-07-07 |
| 82 | Devstral 2 | Mistral | 10.5 | 2 | 2026-07-07 |
| 83 | Nemotron 3 Super 120B A12B | NVIDIA | 10.3 | 1 | 2026-07-03 |
| 84 | Nemotron Cascade 2 30B A3B | NVIDIA | 10.1 | 1 | 2026-07-23 |
| 85 | MiniMax M2.7 | MiniMax | 9.9 | 2 | 2026-07-07 |
| 86 | Gemini 2.5 Pro | 9.7 | 2 | 2026-07-07 | |
| 87 | Gemini 3.1 Flash Lite Preview | 9.7 | 2 | 2026-07-07 | |
| 88 | Mercury 2 | Inception | 9.5 | 1 | 2026-07-21 |
| 89 | Qwen3.6 35B A3B | Alibaba | 9.3 | 2 | 2026-07-14 |
| 90 | Nova 2.0 Pro Preview | Amazon | 9.1 | 3 | 2026-07-03 |
| 91 | Claude Haiku 4.5 | Anthropic | 9.1 | 1 | 2026-07-03 |
| 92 | Nemotron 3.5 Lightning | NVIDIA | 8.9 | 1 | 2026-08-12 |
| 93 | MiMo V2.5 Pro | Xiaomi | 8.7 | 2 | 2026-07-07 |
| 94 | Gemma 4 12B | 8.7 | 1 | 2026-07-25 | |
| 95 | Solar Pro 3 | Upstage | 8.7 | 2 | 2026-07-07 |
| 96 | Mistral Medium 3.1 (Non-Reasoning) | Mistral | 8.2 | 1 | 2026-07-03 |
| 97 | Mistral Small 3.1 | Mistral | 7.4 | 2 | 2026-07-07 |
| 98 | LFM2.5-2.6B | Liquid AI | 7.2 | 1 | 2026-08-22 |
| 99 | gpt-oss-20b | OpenAI | 7 | 1 | 2026-07-03 |
| 100 | NVIDIA Nemotron 3 Nano 4B | NVIDIA | 7 | 2 | 2026-07-08 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.