Text Common-sense & Reading on OpenBookQA
98.6ScoreQwen3.5-Plus
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-PlusParameter Count=397B2026.06 | 98.6 | |
| Opus-4.6Parameter Count=≈800B2026.06 | 97 | |
| GPT-5.4Parameter Count=≈1.5T2026.06 | 96.6 | |
| Qwen3-VL-32BDecoding Mode=Thinking, Model Scale=32B2026.06 | 96.4 | |
| K2.5Parameter Count=≈1T2026.06 | 96.4 | |
| Yuvion VL-32BDecoding Mode=Reasoning, Model Scale=32B2026.06 | 96 | |
| Qwen3-VL-32BDecoding Mode=Instruct, Model Scale=32B2026.06 | 95.4 | |
| Qwen3-VL-8BDecoding Mode=Thinking, Model Scale=8B2026.06 | 93.8 | |
| Yuvion VL-32BDecoding Mode=Instruct, Model Scale=32B2026.06 | 93.8 | |
| Qwen3-VL-8BDecoding Mode=Instruct, Model Scale=8B2026.06 | 93 | |
| Yuvion VL-8BDecoding Mode=Instruct, Model Scale=8B2026.06 | 90.8 | |
| Yuvion VL-8BDecoding Mode=Reasoning, Model Scale=8B2026.06 | 77.8 |