Benchgen

PinchBench — Results

RankModelScore
1gemini-3-flash95.1
2claude-sonnet-4-593.6
3minimax-m2-193.4
4claude-haiku-4-590.2
5kimi-k2-589.2
6claude-opus-4-588.9
7claude-opus-4-688.2
8gemini-3-pro87.7
9claude-sonnet-487.5
10nemotron-3-super-120b-a12b85.9
11gpt-4o85
12glm-4-5-air83.7
13nemotron-3-5-lightning-30b-a3b83.4
14glm-5-182.9
15deepseek-v3-281.1
16qwen3-5-397b-a17b80.7
17gemini-2-5-flash76.6
18gpt-4o-mini76.3
19claude-sonnet-4-668.6
20gpt-5-265.6
21minimax-m2-543.7
22glm-542.8
23step-3-5-flash40.9
24gemini-1-5-pro39.4
25gemini-2-0-flash39.4

PinchBench — Leaderboard

1 phaseActive

PinchBench Leaderboard

No self-reported entries.