Skip to content

Benchmark

Harvey's Legal Agent Benchmark

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.25

Score distribution

17.7%
Mean
19.6%
Median
4.6%
Std dev
10%
10th percentile
23.7%
90th percentile
10%
Min
10%23.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.25 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 K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim23.7%
2Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim19.6%
3Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim19.6%
4Mistral Large 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim15.8%
5Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10%

Data credits: Data by LLM Stats