Alibaba · Updated 4 November 2026
Qwen3.8 27B
Qwen3.8 27B from Alibaba is #35 of 54 models on the Artificial Analysis Intelligence Index, with a score of 20. It costs $1.13 per million tokens ($0.50 in, $3.00 out) and writes 39 tok/s. Its weights are open: anyone can download and run it.
- Intelligence
- 20 · 35th of 54
- Coding
- Not scored yet
- Price per 1M tokens
- $1.13 blended · $0.50 input · $3.00 output
- Output speed
- 39 tok/s
- Time to first token
- 1.4 s
- Context window
- 1M tokens
- Open weights
- Yes
- Released
- 14 August 2026
Settings
| # | Setting | Intelligence | Coding | Price / 1M tokens | Speed |
|---|---|---|---|---|---|
| 1 | Xhigh | 20 | — | $1.13 | 39 tok/s |
| 2 | Medium | 18 | — | $1.13 | 44 tok/s |
| 3 | Low | 16 | — | $1.13 | 45 tok/s |
| 4 | Non-reasoning | 10 | — | $1.13 | 44 tok/s |
The same model at different reasoning settings. Higher settings think longer and usually score higher.
How it compares
| # | Model | Intelligence | Coding | Price / 1M tokens | Speed | Context |
|---|---|---|---|---|---|---|
| 1 | Qwen3.8 27B Alibaba · open weights | 20 | — | $1.13 | 39 tok/s | 1M |
| 2 | Gemini 4 Carbon Google | 60 | — | $8.00 | 92 tok/s | — |
| 3 | DeepSeek V4 Pro 0813 DeepSeek · open weights | 23 | — | $1.98 | 73 tok/s | 1M |
| 4 | Nanbeige4.3-33B Nanbeige | 20 | — | — | — | — |
| 5 | MiniMax-M3 MiniMax · open weights | 19 | — | $0.53 | 102 tok/s | 1M |
| 6 | MiMo-V2.6-Flash Xiaomi · open weights | 27 | — | $0.17 | 30 tok/s | 1.1M |
Cheaper alternative within 3 points: MiMo-V2.6-Flash at $0.17 per million tokens.
Data: Artificial Analysis (intelligence and coding indexes, prices, speed) and OpenRouter (open weights, context windows). Updated 4 November 2026; refreshed every 6 hours.
More rankings
All rankings · Best overall · Best open model · Best value · Cheapest good model · Best for coding · Fastest · Longest context · Price table