Dialogue Memory Reasoning on LongMemEval
76.4AccuracyQwenLong-L1.5-30B-A3B
Evaluation Results
| Method | Links | |
|---|---|---|
| QwenLong-L1.5-30B-A3B2025.12 | 76.4 | |
| Qwen3-30B-A3B-Thinking-25072025.12 | 60.8 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| QwenLong-L1.5-30B-A3B2025.12 | 76.4 | |
| Qwen3-30B-A3B-Thinking-25072025.12 | 60.8 |