Code Generation on Code Generation
77.1AccuracyGrok-4-Fast
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Grok-4-Fast2026.01 | 77.1 | 74.8 | |
| GPT-4.1-MINI2026.01 | 77.1 | 50.8 | |
| Deepseek-V3.12026.01 | 77.1 | 90.1 | |
| Qwen3-235B-A22B-Instruct2026.01 | 77.1 | 84.7 | |
| Claude-Sonnet-4-52026.01 | 77.1 | 92.6 | |
| DeepSeek-R1-Distill-Qwen-32B2026.01 | 76.8 | 92.1 | |
| Gemini-2.5-Flash2026.01 | 76.1 | 86.6 | |
| DeepSeek-R1-Distill-Qwen-14B2026.01 | 74.8 | 81.7 | |
| Qwen2.5-72B-Instruct2026.01 | 72.9 | 64.2 | |
| Qwen2.5-32B-Instruct2026.01 | 72.3 | 55.9 | |
| Qwen2.5-14B-Instruct2026.01 | 66.2 | 42.8 | |
| Qwen2.5-7B-Instruct2026.01 | 65.3 | 51.2 | |
| DeepSeek-R1-Distill-Qwen-7B2026.01 | 63.4 | 86.4 | |
| QwQ-32B2026.01 | 62.4 | 50 | |
| Meta-Llama-3.1-70B-Instruct2026.01 | 62.4 | 61.2 | |
| DeepSeek-R1-Distill-Llama-8B2026.01 | 60.2 | 77.2 | |
| OpenReasoning-Nemotron-14B2026.01 | 52.2 | 61.6 | |
| Qwen3-32B2026.01 | 48.1 | 78.1 | |
| Meta-Llama-3.1-8B-Instruct2026.01 | 45.9 | 55.6 | |
| GLM-Z1-32B2026.01 | 43.3 | 38.2 | |
| Qwen2.5-1.5B-Instruct2026.01 | 31.5 | 61.6 |