Instruction Following on AgentIF
66.1CSRClaude-Opus-4.7
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude-Opus-4.7Stage=-2026.05 | 66.1 | |
| R1-0528-Qwen3-8BStage=Iter32026.05 | 62.6 | |
| R1-0528-Qwen3-8BStage=Iter22026.05 | 62.3 | |
| R1-0528-Qwen3-8BStage=Iter12026.05 | 61.2 | |
| Qwen2.5-7B-InstructStage=Iter32026.05 | 60.5 | |
| Qwen2.5-7B-InstructStage=Iter22026.05 | 59.8 | |
| Distill-Qwen-14BStage=Iter12026.05 | 59.7 | |
| Qwen2.5-7B-InstructStage=Iter12026.05 | 59.3 | |
| Distill-Qwen-14BStage=Iter22026.05 | 58.9 | |
| GPT-4oStage=-2026.05 | 58.5 | |
| Distill-Qwen-14BStage=Iter32026.05 | 58.2 | |
| QwQ-32BStage=-2026.05 | 58.1 | |
| Llama-3.1-8B-InstructStage=Iter32026.05 | 57.4 | |
| R1-0528-Qwen3-8BStage=BASE2026.05 | 57.4 | |
| Self-Supervised-7BStage=-2026.05 | 56.7 | |
| VERIF-8BStage=-2026.05 | 56.6 | |
| Llama-3.1-8B-InstructStage=Iter12026.05 | 55.8 | |
| Llama-3.1-8B-InstructStage=Iter22026.05 | 55.2 | |
| Distill-Qwen-14BStage=BASE2026.05 | 54.5 | |
| Qwen2.5-7B-InstructStage=BASE2026.05 | 54.2 | |
| SPAR-8B-DPOStage=-2026.05 | 53.6 | |
| Llama-3.1-8B-InstructStage=BASE2026.05 | 53.4 | |
| RAIF-7BStage=-2026.05 | 51.9 | |
| Qwen2.5-1.5B-InstructStage=Iter32026.05 | 47.5 | |
| Crab-7B-DPOStage=-2026.05 | 47.2 | |
| Qwen2.5-1.5B-InstructStage=Iter12026.05 | 46.2 | |
| Qwen2.5-1.5B-InstructStage=Iter22026.05 | 45.6 | |
| Conifer-7B-DPOStage=-2026.05 | 44.3 | |
| Qwen2.5-1.5B-InstructStage=BASE2026.05 | 42.8 |