General Task (Agentic Coding) on IFBench
77.1ScoreGemini 3.1 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3.1 ProSource=artificialanalysis.ai2026.03 | 77.1 | |
| MiniMax M2.7Source=artificialanalysis.ai2026.03 | 75.7 | |
| GPT-5.4Source=artificialanalysis.ai2026.03 | 73.9 | |
| GLM-5Source=artificialanalysis.ai2026.03 | 72.3 | |
| KAT-Coder-V2Evaluation Environment=KwaiEnv2026.03 | 67 | |
| Claude Opus 4.6Source=artificialanalysis.ai2026.03 | 53.1 |