Benchmark
SWE-ContextBench Lite Related · Resolved · CMB paper run
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 2
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 32%
- Mean
- 36.4%
- Median
- 9.8%
- Std dev
- 19.2%
- 10th percentile
- 45.5%
- 90th percentile
- 19.2%
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: FullContext · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 37.4% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: Mem0 · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 38.4% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: MemOS · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 39.4% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: NoMemory · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 43.4% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: OpenViking · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 36.4% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: RepoMemory · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 45.5% |
| Claude Sonnet 5 (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: TriLink · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 47.5% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: FullContext · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 23.2% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: Mem0 · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 25.3% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: MemOS · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 25.3% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: NoMemory · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 20.2% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: OpenViking · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 19.2% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: RepoMemory · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 19.2% |
| DeepSeek V4 Flash (CMB paper label)SWE-ContextBench Lite Related · CMB paper run · 99 tasks · mini-swe-agent · memory: TriLink · F2P-based resolution · candidate snapshot, reasoning effort, and run count not stated· Reported by Tencent Hunyuan· via BenchBoard docs | 28.3% |