Qwen3.8 27Bopen
Alibaba
49.3#154 of 427 overall
- Input / output
- US$ 0,15 / US$ 1,88 US$ per 1M tokens
- Context
- 1M tokens
- Release
- 08/14/2026 release date
- Speed
- 39 tok/s first token in 1.23 s
Family history
The 3 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 |
|---|---|---|---|---|---|
| Qwen3.5-27B | 02/25/2026 | 48.1 | #163 | — | 1409 |
| Qwen3.6 27B | 04/27/2026 | 47.9 | #168 | — | — |
| Qwen3.8 27B | 08/14/2026 | 49.3 | #154 | 20.1 | 1438 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 58.4 | 23% | LiveBench |
| AA Intelligence Index weight 3 | 20.1 | 35% | Artificial Analysis |
| Arena text (Elo) weight 2 | 1438 | 68% | LMArena |
| Arena WebDev (Elo) weight 1 | 1590 | 76% | LMArena |
| Arena vision (Elo) weight 0.5 | 1269 | 66% | LMArena |
| Humanity's Last Exam weight 1 | 33.9 | 83% | Artificial Analysis |
| Terminal-Bench weight 1 | 5.6 | 66% | Artificial Analysis |
| GPQA Diamond | 90.5 | 91% | Artificial Analysis |
| Long-context reasoning | 82.0 | 92% | Artificial Analysis |
| LiveBench long agentic | 20.6 | 32% | LiveBench |
| LiveBench reasoning | 80.0 | 26% | LiveBench |
| LiveBench coding | 86.8 | 61% | LiveBench |
| LiveBench browser | 24.2 | 19% | LiveBench |
| LiveBench data analysis | 76.6 | 53% | LiveBench |
| LiveBench research | 59.4 | 10% | LiveBench |
| LiveBench design | 75.9 | 39% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 49.3 | #70 | LiveBench long agentic, Terminal-Bench |
| Coding | 62.5 | #25 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 62.5 | #126 | LiveBench reasoning, Humanity's Last Exam, GPQA Diamond |
| Data analysis | 51.6 | #15 | LiveBench data analysis |
| Research | 50.5 | #170 | LiveBench research, Long-context reasoning |
| Design | 55.0 | #43 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 34.7 | #26 | LiveBench browser |
| Chat | 59.1 | #64 | Arena text (Elo) |
| Vision | 57.9 | #37 | 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.