Skip to content

Benchmark

BigCodeBench

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models and systems measured
3
Scores recorded
3
Sources
2
IQ weight
No weight published

Score distribution

57.2%
Mean
60.6%
Median
12.1%
Std dev
41%
10th percentile
70.1%
90th percentile
41%
Min
41%70.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4.1 Flash Basepass@1 · 3-shot· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.6%
MiMo V2 Flash Baseofficial Base table · 0-shot· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.1%

Data credits: Data by LLM Stats · 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.