Benchmark
PinchBench
Coding benchmarks compare models on programming tasks. Scores are percentages.
- Models measured
- 58
- Scores recorded
- 58
- Sources
- 2
- IQ weight
- 1.13
Score distribution
- 75.1%
- Mean
- 80.9%
- Median
- 15.6%
- Std dev
- 54.8%
- 10th percentile
- 89.7%
- 90th percentile
- 21.4%
- Min
This benchmark has a weight of 1.13 for chat models, measured over 58 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | GLM 5.1· PinchBench data | 60% |
| 52 | Claude Fable 5· PinchBench data | 54.8% |
| 53 | Nemotron 3 Super 120B A12B· PinchBench data | 53.8% |
| 54 | GPT OSS 120B· PinchBench data | 45.2% |
| 55 | Nova 2 Lite· PinchBench data | 37.2% |
| 56 | GPT OSS 20b· PinchBench data | 33.9% |
| 57 | Mercury 2· PinchBench data | 32.7% |
| 58 | GPT-5.5 Pro· PinchBench data | 21.4% |
Showing 51–58 of 58 results.
Data credits: Data by LLM Stats