| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-deepswe | Muse Spark 1.3 (max effort) (mini-swe-agent) | – | Pass@1: 0.754 |
| code-generation-on-terminal-bench-2-1 | Muse Spark 1.3 (max) (Muse Code) | – | Accuracy: 88.8 |
| computer-use-agents-on-osworld-2-0 | Muse Spark 1.3 (max) | – | Success Rate: 32.0 |