LongBench
LongBench results reported for 2 models across 1 version. Updated 2026-10-02.
Report an issueVersions
1 version · Metric: Multiple-choice accuracy
| Version | Released | Models | Results |
|---|---|---|---|
| LongBench v2Latest | December 20, 2024 | 2 | 2 |
Recently reported results: LongBench v2
Latest version: LongBench v2
| Model | Score | Source |
|---|---|---|
| Qwen3.8-Max | 66.3% | qwen.ai for Qwen3.8-Max on LongBench v2 (opens in a new tab)Multiple-choice accuracyReported Launch postQwen TeamSelf-reportedRecord for Qwen3.8-Max on LongBench v2 |
| Qwen3.6-Plus | 62.0% | qwen.ai for Qwen3.6-Plus on LongBench v2 (opens in a new tab)Multiple-choice accuracyReported Launch postQwen TeamSelf-reportedRecord for Qwen3.6-Plus on LongBench v2 |