Claw-Eval
AI benchmark results and model performance
Type: percentageAgents
Recorded results
13
Average score
58.90%
Score range
23.80% - 75%
Leading model
75% - GLM 5V Turbo
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| GLM 5V Turbo | 01 Apr 2026 | 75% | - | Yes | Source | |
| DeepSeek V4 Pro | 24 Apr 2026 | 65.80% | Multi Turn; Hugging Face evaluation result | Yes | Source | |
| Qwen 3.7 Max | 21 May 2026 | 65.20% | - | Yes | Source | |
| MiMo V2.5 | 23 Apr 2026 | 63.20% | Multi Turn; Hugging Face evaluation result | Yes | Source | |
| MiMo V2 Pro | 18 Mar 2026 | 61.50% | - | Yes | Source | |
| MiMo V2 TTS (Free) | 18 Mar 2026 | 61.50% | inferred modality/version alias from mimo-v2-pro | Yes | Source | |
| Qwen 3.6 Plus | 01 Apr 2026 | 58.70% | - | Yes | Source | |
| DeepSeek V4 Flash | 24 Apr 2026 | 57.90% | Multi Turn; Hugging Face evaluation result | Yes | Source | |
| MiMo V2 Omni | 18 Mar 2026 | 54.80% | - | Yes | Source |
