Skip to content

Benchmark

GDPval Rubrics

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
2
Scores recorded
4
Sources
2
IQ weight
No weight published

Score distribution

77.3%
Mean
74.8%
Median
4.4%
Std dev
74.7%
10th percentile
84.8%
90th percentile
74.7%
Min
74.7%84.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.8%
2MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.8%
3MiniMax M3public GDPval cases · pointwise public rubrics· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.8%
4MiniMax M3official model-page overview figure · rounded· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.7%

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.