HLAB-Vals-1.1 leaderboard
As of November 22, 2026, among the results listed here, Qwen4 Max has the highest reported HLAB-Vals-1.1 score, 21.3, published by Qwen on August 3, 2026, ahead of Qwen3.8 Max (0902) at 15.4. 2 models have a HLAB-Vals-1.1 result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Qwen4 Max | 21.3 | Not published | Qwen | August 3, 2026 · read from the maker's chart |
| 2 | Qwen3.8 Max (0902) | 15.4 | Not published | Qwen | August 3, 2026 · read from the maker's chart |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 21.3 to 15.4 across 2 models.
- Freshness
- Published August 3, 2026.
- Charts
- Some values were read from charts in the announcements. Two independent readings had to match exactly.
What HLAB-Vals-1.1 measures
HLAB-Vals-1.1 tests AI agents on legal work involving documents, spreadsheets, and presentations; the results do not explain what its score means. Source: HLAB-Vals-1.1 Leaderboard and Methodology