Benchmark
SWE-Atlas
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
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 39%
- Mean
- 35.2%
- Median
- 8.8%
- Std dev
- 30.6%
- 10th percentile
- 51.1%
- 90th percentile
- 30.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Mercury 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.1% |
| 2 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.2% |
| 3 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.6% |
Data credits: Data by LLM Stats