Graph traversal on GraphWalks
89.87Parents ScoreDeepSeek-V3.2-Thinking
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| DeepSeek-V3.2-Thinking2026.05 | 89.87 | 80.26 | 85.39 | — | |
| Kimi-K2-Thinking2026.05 | 84.34 | 75.17 | 80.04 | — | |
| Qwen3-30B-A3B-Thinking + ACC2026.05 | 81.5 | 72.95 | 77.51 | — | |
| GPT-5.1-Thinking2026.05 | 81.41 | 29.41 | 57.14 | — | |
| GLM-4.6-Thinking2026.05 | 80.29 | 77.41 | 78.95 | — | |
| Qwen3-235B-A22B-Thinking2026.05 | 78.53 | 74.45 | 76.63 | — | |
| GPT-OSS-120B2026.05 | 75.92 | 61.82 | 69.34 | — | |
| Qwen3-30B-A3B-Thinking2026.05 | 71.19 | 68.47 | 69.92 | — | |
| ACCBase Model=Qwen3-30B-A3B-Thinking2026.05 | — | — | — | 77.51 | |
| Qwen2.5-14B-LongRLVRParameters=14B2026.05 | — | — | — | 22.78 | |
| Qwen2.5-7B-LongPO-128KParameters=7B, Context Limit=128K2026.05 | — | — | — | 12.97 | |
| Qwen2.5-7B-LongRLVRParameters=7B2026.05 | — | — | — | 15.72 | |
| Qwen3-30B-A3B-ThinkingModel Role=Base Model, Parameters=30B2026.05 | — | — | — | 69.92 | |
| QwenLong-L1.5-30BParameters=30B, Context Limit=256K2026.05 | — | — | — | 73.85 |