Benchmark
Multi-SWE-Bench
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 10
- Scores recorded
- 13
- Sources
- 2
- IQ weight
- 3.12
Score distribution
- 46.5%
- Mean
- 50.3%
- Median
- 7.7%
- Std dev
- 36.2%
- 10th percentile
- 52.7%
- 90th percentile
- 25.8%
- Min
This benchmark has a weight of 3.12 for chat models, measured over 10 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 | MiniMax M2.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.7% |
| 2 | MiniMax M2.7MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.7% |
| 3 | MiniMax M2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.3% |
| 4 | MiniMax M2.5main capability figure· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.3% |
| 5 | MiniMax M2.5MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.3% |
| 6 | Claude Sonnet 4.6MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51% |
| 7 | Claude Opus 4.6MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.3% |
| 8 | MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.4% |
| 9 | GPT 5.4MiniMax M2.7 official benchmark overview · exact harness/version not stated· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49% |
| 10 | Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42% |
| 11 | Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.9% |
| 12 | MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 36.2% |
| 13 | Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 25.8% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats