Benchmark
AlgoTune
Coding benchmarks compare models on programming tasks. Scores are percentages.
All coding benchmarksScores from Epoch AI Benchmarking Hub data.
- Models measured
- 18
- Scores recorded
- 18
- Sources
- 1
- IQ weight
- 0.83
Score distribution
- 1.6%
- Mean
- 1.5%
- Median
- 0.227%
- Std dev
- 1.3%
- 10th percentile
- 1.9%
- 90th percentile
- 1.3%
- Min
This benchmark has a weight of 0.83 for chat models, measured over 18 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 |
|---|---|---|
| 1 | GPT 5.2medium· Epoch AI Benchmarking Hub data | 2% |
| 2 | Gemini 3.1 Pro Preview· Epoch AI Benchmarking Hub data | 2% |
| 3 | GPT 5.4high· Epoch AI Benchmarking Hub data | 1.9% |
| 4 | Gemini 3 Pro Preview· Epoch AI Benchmarking Hub data | 1.8% |
| 5 | Claude Opus 4.5· Epoch AI Benchmarking Hub data | 1.8% |
| 6 | o4 Minihigh· Epoch AI Benchmarking Hub data | 1.7% |
| 7 | DeepSeek R1· Epoch AI Benchmarking Hub data | 1.7% |
| 8 | GPT 5high· Epoch AI Benchmarking Hub data | 1.7% |
| 9 | Claude Sonnet 4.5· Epoch AI Benchmarking Hub data | 1.5% |
| 10 | GLM 4.5thinking· Epoch AI Benchmarking Hub data | 1.5% |
| 11 | Gemini 2.5 Pro· Epoch AI Benchmarking Hub data | 1.5% |
| 12 | Claude Opus 4.6high· Epoch AI Benchmarking Hub data | 1.5% |
| 13 | Qwen3 Coder· Epoch AI Benchmarking Hub data | 1.4% |
| 14 | GPT OSS 120Bhigh· Epoch AI Benchmarking Hub data | 1.4% |
| 15 | GPT-5 minihigh· Epoch AI Benchmarking Hub data | 1.4% |
| 16 | Claude Opus 4.1· Epoch AI Benchmarking Hub data | 1.3% |
| 17 | Claude Opus 4· Epoch AI Benchmarking Hub data | 1.3% |
| 18 | GPT-5 Promedium· Epoch AI Benchmarking Hub data | 1.3% |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)