Skip to content

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
3.44.2
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude 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
2GLM 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
3Kimi 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
4GLM 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

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.