Skip to content

Benchmark

Harvey LAB-AA

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

Models measured
5
Scores recorded
6
Sources
2
IQ weight
0.00

Score distribution

51.5%
Mean
90.7%
Median
40.5%
Std dev
10%
10th percentile
94.6%
90th percentile
10%
Min
10%94.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 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
1Kimi K3criterion pass rate · snapshot 2026-07-23· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94.6%
2Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.7%
3Gemini 3.7 Flashofficial model-card metric· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.7%
4Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim13.1%
5Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10%
6Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10%

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