PinchBench
Progress Over Time
Interactive timeline showing model performance evolution on PinchBench
State-of-the-art frontier
Open
Proprietary
PinchBench Leaderboard
7 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 550B | 262K | $0.50 / $2.20 | |||
| 2 |  NVIDIA | 74B | — | — | ||
| 3 | 30B | 262K | $0.08 / $0.20 | |||
| 4 |  Xiaomi | — | — | — | ||
| 5 | Xiaomi | 1.0T | — | — | ||
| 6 |  Zhipu AI | — | — | — | ||
| 7 |  Liquid AI | 3B | — | — |
Notice missing or incorrect data?
What is PinchBench?
PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.
PinchBench is a text benchmark evaluating models on agents and code tasks. LLM Stats tracks 7 models on this benchmark, scored on a 0–1 scale. The current average is 0.8, with the leader at 0.9.
Compare leaders on the best AI for agents and best AI for code leaderboards.
Current leaders
Nemotron 3 Ultra (550B A55B) from NVIDIA currently leads the PinchBench leaderboard with a score of 0.900 across 7 evaluated AI models.
FAQ
Common questions about the PinchBench benchmark and leaderboard.