Benchmark
Deepswe Pass@4
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
All coding benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 26
- Scores recorded
- 69
- Sources
- 1
- IQ weight
- 1.95
Score distribution
- 76%
- Mean
- 80.5%
- Median
- 15.5%
- Std dev
- 60.2%
- 10th percentile
- 88.5%
- 90th percentile
- 4.4%
- Min
This benchmark has a weight of 1.95 for chat models, measured over 26 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
Showing 1–50 of 69 results.
Tokens the model generated per task, as measured by the source. Comparable within this benchmark only.
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)