Benchmark
Surge AI Blind Coding Quality
Coding benchmarks compare models on programming tasks. Higher scores are better.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 3.7
- Mean
- 3.6
- Median
- 0.309
- Std dev
- 3.4
- 10th percentile
- 4.2
- 90th percentile
- 3.4
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 51–5 blind human rating · Surge AI· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 4.2 |
| 2 | GLM 5.31–5 blind human rating · Surge AI· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 3.6 |
| 3 | Kimi K31–5 blind human rating · Surge AI· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 3.6 |
| 4 | GLM 5.21–5 blind human rating · Surge AI· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 3.4 |