Qwen3.8 Max (0902)
Alibaba
68.3#48 of 427 overall
- Input / output
- US$ 2,00 / US$ 6,00 US$ per 1M tokens
- Context
- 1M tokens
- Release
- 09/03/2026 release date
- Weights
- Closed
- Speed
- 38 tok/s first token in 2.11 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 |
|---|---|---|---|
| LiveBench weight 3 | 61.6 | 32% | LiveBench |
| AA Intelligence Index weight 3 | 33.6 | 67% | Artificial Analysis |
| Arena text (Elo) weight 2 | 1483 | 93% | LMArena |
| Arena WebDev (Elo) weight 1 | 1676 | 91% | LMArena |
| Arena vision (Elo) weight 0.5 | 1313 | 92% | LMArena |
| Humanity's Last Exam weight 1 | 43.1 | 92% | Artificial Analysis |
| Terminal-Bench weight 1 | 38.9 | 89% | Artificial Analysis |
| GPQA Diamond | 92.8 | 97% | Artificial Analysis |
| Long-context reasoning | 80.3 | 88% | Artificial Analysis |
| LiveBench long agentic | 29.9 | 52% | LiveBench |
| LiveBench reasoning | 88.2 | 52% | LiveBench |
| LiveBench coding | 60.3 | 10% | LiveBench |
| LiveBench browser | 49.4 | 44% | LiveBench |
| LiveBench data analysis | 78.4 | 61% | LiveBench |
| LiveBench research | 69.9 | 29% | LiveBench |
| LiveBench design | 78.6 | 68% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 63.5 | #27 | LiveBench long agentic, Terminal-Bench |
| Coding | 50.1 | #56 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 72.6 | #57 | LiveBench reasoning, Humanity's Last Exam, GPQA Diamond |
| Data analysis | 55.6 | #13 | LiveBench data analysis |
| Research | 55.8 | #134 | LiveBench research, Long-context reasoning |
| Design | 69.4 | #13 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 46.8 | #18 | LiveBench browser |
| Chat | 71.5 | #15 | Arena text (Elo) |
| Vision | 71.2 | #9 | Arena vision (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.