Qwen3 Max Thinking
Alibaba
66.5#56 of 427 overall
- Input / output
- free / free US$ per 1M tokens
- Context
- — tokens
- Release
- 01/26/2026 release date
- Weights
- Closed
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 7 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| Qwen-Max | — | — | — | — | 1282 |
| Qwen2.5 Max | 01/28/2025 | 31.5 | #337 | — | 1367 |
| Qwen3 Max Thinking | 01/26/2026 | 66.5 | #56 | — | 1439 |
| Qwen3.5-Max-Preview | — | — | — | — | 1470 |
| Qwen3.6 Max Preview | 04/20/2026 | 67.1 | #53 | — | 1447 |
| Qwen3.7 Max | 05/21/2026 | 72.5 | #33 | — | 1475 |
| Qwen3.8 Max (0902) | 09/03/2026 | 68.3 | #48 | 33.6 | 1483 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1439 | 70% | LMArena |
| Humanity's Last Exam weight 1 | 28.0 | 77% | Artificial Analysis |
| GPQA Diamond | 86.1 | 81% | Artificial Analysis |
| Long-context reasoning | 74.3 | 72% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Reasoning | 69.3 | #81 | Humanity's Last Exam, GPQA Diamond |
| Research | 61.0 | #90 | Long-context reasoning |
| Chat | 59.9 | #59 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.