Writing on LongBench-Write (LB)
97.8LB ScoreClaude 3.7
Evaluation results
| Method | Links | |
|---|---|---|
| Claude 3.7Model Category=General Closed-source Models2026.04 | 97.8 | |
| Qwen3-32BModel Category=General Open-source Models2026.04 | 93.2 | |
| Claude 3.5Model Category=General Closed-source Models2026.04 | 89.3 | |
| Qwen2.5-7B-Instruct + SFT + RL-TCERModel Category=Finetuned Open-source Models, Training Stage=SFT + RL-TCER2026.04 | 86.3 | |
| Qwen3-8BModel Category=General Open-source Models2026.04 | 85.2 | |
| Qwen2.5-7B-Instruct + SFT + RL-EndoRModel Category=Finetuned Open-source Models, Training Stage=SFT + RL-EndoR2026.04 | 84.5 | |
| GPT-4oModel Category=General Closed-source Models2026.04 | 83.1 | |
| Qwen2.5-7B-Instruct + SFTModel Category=Finetuned Open-source Models, Training Stage=SFT2026.04 | 83.1 | |
| Qwen2.5-32B-InstructModel Category=General Open-source Models2026.04 | 78.8 | |
| Qwen2.5-7B-InstructModel Category=Finetuned Open-source Models, Training Stage=Base2026.04 | 74.7 | |
| Llama3.1-8B-InstructModel Category=General Open-source Models2026.04 | 60.3 |