Skip to content

Benchmark

LiveSQLBench

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

Models measured
1
Scores recorded
2
Sources
2
IQ weight
No weight published

Score distribution

40.2%
Mean
40.2%
Median
0%
Std dev
40.2%
10th percentile
40.2%
90th percentile
40.2%
Min

Leaderboard

#ModelScore
1MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.2%
2MiniMax M3LiveSQLBench-Base-Full v1 · 600 questions · Claude Code· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.40.2%

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. · Data by LLM Stats