Functional correctness for backend applications on Baxbench
69.8Functional CorrectnessClaude-Sonnet-4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-Sonnet-4.5Model Type=Proprietary2025.12 | 69.8 | |
| GPT-5Model Type=Proprietary2025.12 | 67.1 | |
| DeepSeek-V3.1-Nex-N1Model Type=Open Source, Parameter Scale=> 100B2025.12 | 59.7 | |
| Kimi-K2-thinkingModel Type=Open Source, Parameter Scale=> 100B2025.12 | 57.4 | |
| DeepSeek-V3.1Model Type=Open Source, Parameter Scale=> 100B2025.12 | 50.1 | |
| Gemini-2.5-proModel Type=Proprietary2025.12 | 49.7 | |
| Qwen3-32BModel Type=Open Source, Parameter Scale=< 100B2025.12 | 35.6 | |
| Qwen3-32B-Nex-N1Model Type=Open Source, Parameter Scale=< 100B2025.12 | 34.8 | |
| GLM-4.6Model Type=Open Source, Parameter Scale=> 100B2025.12 | 32.1 | |
| Qwen3-30B-A3BModel Type=Open Source, Parameter Scale=< 100B2025.12 | 27.2 | |
| Minimax-M2Model Type=Open Source, Parameter Scale=> 100B2025.12 | 23.4 | |
| Qwen3-30B-A3B-Nex-N1Model Type=Open Source, Parameter Scale=< 100B2025.12 | 13.6 | |
| InternLM3-8BModel Type=Open Source, Parameter Scale=< 100B2025.12 | 1.6 | |
| InternLM3-8B-Nex-N1Model Type=Open Source, Parameter Scale=< 100B2025.12 | 0.3 |