Benchmark
Arena Agent Bash Recovery Steps
Agentic benchmarks measure how well models carry out tasks that take several steps. Higher scores are better.
All agentic benchmarksScores from LMArena data.
- Models measured
- 50
- Scores recorded
- 52
- Sources
- 1
- IQ weight
- 2.12
Score distribution
- 0.008
- Mean
- 0.023
- Median
- 0.091
- Std dev
- -0.075
- 10th percentile
- 0.096
- 90th percentile
- -0.256
- Min
This benchmark has a weight of 2.12 for chat models, measured over 50 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 |
|---|---|---|
| 51 | Gemini 3.1 Pro Preview· LMArena data | -0.233 |
| 52 | Solar Pro 4· LMArena data | -0.256 |
Showing 51–52 of 52 results.
Data credits: LMArena, CC BY 4.0 (licence)