LLM Stats leaderboard
14 scores · 14 models · first recorded Oct 2, 2026
higher is better · scale 0–1 · record Claw-Eval
Best reported score
80.9%Kimi K2.6 · LLM Stats leaderboard
14 models tested · 1 sources · 1 source documents · latest report Aug 4, 2026
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
Scores stay separate per source — never merged into one cross-source ranking.
14 scores · 14 models · first recorded Oct 2, 2026
higher is better · scale 0–1 · record Claw-Eval
| Model | Value (%) | Reported | Score type | Recorded |
|---|---|---|---|---|
| LFM2.5-2.6B | 62.8% | Aug 4, 2026 | unspecified | Oct 2, 2026 |
| Hy3 | 68.5% | Jul 6, 2026 | unspecified | Oct 2, 2026 |
| MiniMax M3 | 74.5% | Jun 1, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7-Plus | 62.7% | May 31, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Max | 65.2% | May 19, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5-Pro | 64% | Apr 27, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5 | 63.2% | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-27B | 60.6% | Apr 21, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.6 | 80.9% | Apr 20, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-35B-A3B | 50% | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5V-Turbo | 75% | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Plus | 58.7% | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2-Pro | 61.5% | Mar 18, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2-Omni | 54.8% | Mar 18, 2026 | unspecified | Oct 2, 2026 |
every document that defines or reports scores
| other | – | Claw-Eval– |
Records are located via the tracking corpus (ktwu01/benchmark-radar live dataset). Every row cites its source document.