| # | Model | Vendor | Best score | Runs | Last seen |
|---|---|---|---|---|---|
| 1 | Kimi K3 | Moonshot | 33.4 | 1 | 2026-08-24 |
| 2 | GPT-5.6 Sol | OpenAI | 33 | 2 | 2026-08-24 |
| 3 | Grok4.5 | SpaceXAI | 33 | 1 | 2026-08-23 |
| 4 | Claude Opus 4.8 | Anthropic | 27.6 | 1 | 2026-08-24 |
| 5 | GLM-5.2 Full Open Source | Z.ai | 26.8 | 2 | 2026-07-30 |
| 6 | Claude Fable 5 | Anthropic | 26.8 | 2 | 2026-08-24 |
| 7 | DeepSeek-V4-Pro | DeepSeek | 26 | 2 | 2026-07-30 |
| 8 | GPT-5.6 Luna | OpenAI | 24.3 | 1 | 2026-07-30 |
| 9 | Inkling | Thinking Machines | 23.7 | 3 | 2026-07-30 |
| 10 | Inkling-Small | Thinking Machines | 23.7 | 3 | 2026-08-23 |
| 11 | muse-glimmer-30b | Meta | 23.5 | 1 | 2026-08-23 |
| 12 | Solar Pro4 | Upstage | 23 | 1 | 2026-08-23 |
| 13 | DeepSeek-V4-Flash | DeepSeek | 22.9 | 2 | 2026-07-30 |
| 14 | Kimi K2.6 | Moonshot | 20.6 | 2 | 2026-07-30 |
| 15 | Gemini 3.5 Flash Lite | 16.5 | 1 | 2026-07-30 | |
| 16 | Gemini 3.1 Pro | 16.5 | 1 | 2026-07-16 | |
| 17 | Kimi K2.5 | Moonshot | 14.2 | 2 | 2026-07-30 |
| 18 | Qwen3.5 397B A17B | Alibaba | 13.4 | 2 | 2026-07-30 |
| 19 | MiniMax M3 | MiniMax | 13 | 1 | 2026-07-30 |
| 20 | MiMo V2.5 Pro | Xiaomi | 9 | 2 | 2026-07-30 |
| 21 | MiniMax M2.7 | MiniMax | 8.9 | 2 | 2026-07-30 |
| 22 | LFM2.5-2.6B | Liquid AI | 5.7 | 1 | 2026-08-23 |
Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.