PinchBench
AI benchmark results and model performance
Type: percentageAgents
Recorded results
6
Average score
83.53%
Score range
80.70% - 91.90%
Leading model
91.90% - Trinity Large Thinking
Scores over time
Individual benchmark scores plotted by date.
Model results
| Organisation | Models | Reported | Top score | Info | Self reported | Source |
|---|---|---|---|---|---|---|
| Trinity Large Thinking | 01 Apr 2026 | 91.90% | Hugging Face model card benchmark table (arcee-ai/Trinity-Large-Thinking) | Yes | Source | |
| Nemotron 3.5 Lightning 30B A3B | 11 Aug 2026 | 85.37% | NVIDIA release evaluation suite | Yes | Source | |
| MiMo V2 Omni | 18 Mar 2026 | 81.20% | - | Yes | Source | |
| MiMo V2 Pro | 18 Mar 2026 | 81% | - | Yes | Source | |
| MiMo V2 TTS (Free) | 18 Mar 2026 | 81% | inferred modality/version alias from mimo-v2-pro | Yes | Source | |
| GLM 5V Turbo | 01 Apr 2026 | 80.70% | - | Yes | Source |
