Benchmark
Legal Agent Benchmark
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages.
All agentic benchmarksScores from LLM Stats data.
- Models measured
- 16
- Scores recorded
- 16
- Sources
- 1
- IQ weight
- 1.37
Score distribution
- 5.6%
- Mean
- 5.4%
- Median
- 5.7%
- Std dev
- 0%
- 10th percentile
- 13.3%
- 90th percentile
- 0%
- Min
This benchmark has a weight of 1.37 for chat models, measured over 16 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GLM 5.3 FlashX Legal· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 19.2% |
| 2 | Claude Fable 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 13.3% |
| 3 | Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 11.7% |
| 4 | Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 11.7% |
| 5 | Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 8.3% |
| 6 | Claude Opus 4.7· LLM Stats data | 7.1% |
| 7 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 5.8% |
| 8 | Claude Sonnet 4.6· LLM Stats data | 5.4% |
| 9 | Claude Opus 4.6· LLM Stats data | 4.2% |
| 10 | GPT 5.5· LLM Stats data | 2.1% |
| 11 | Gemini 3.5 Flash· LLM Stats data | 0.8% |
| 12 | GPT 5.4· LLM Stats data | 0.4% |
| 13 | Gemini 3 Flash· LLM Stats data | 0% |
| 14 | Gemini 3.1 Flash Lite· LLM Stats data | 0% |
| 15 | Gemini 3.1 Pro Preview· LLM Stats data | 0% |
| 16 | GPT-5.4 mini· LLM Stats data | 0% |
Data credits: Data by LLM Stats