Skip to content

Benchmark

VIBE-Pro

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

Models measured
5
Scores recorded
8
Sources
2
IQ weight
1.11

Score distribution

53.3%
Mean
55.6%
Median
4.7%
Std dev
54.2%
10th percentile
55.6%
90th percentile
41%
Min
41%56.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.11 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Sonnet 4.6MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.1%
2Claude Opus 4.6MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.6%
3MiniMax M2.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.6%
4MiniMax M2.7MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.55.6%
5MiniMax M2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.2%
6MiniMax M2.5main capability figure · average· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.2%
7MiniMax M2.5MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.2%
8Gemini 3.1 Pro PreviewMiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.41%

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