Q
Qwen3.8 27B
The strongest open model you can run on a Mac: LiveBench design 75.9 beats Gemini 4 Argon
Intelligence v5
— v4.3.2 33.7
Leaderboard rank
—
Input / output
$0.10/$0.40
Blended 3:1
$0.17
Output speed
180 tok/s
Value
—
Capability profile Normalised to the field maximum
Specifications
Vendor
Alibaba Qwen
Released
2026-09
Weights
Open (Apache-2.0)
Context
262,144 tokens
Max output
Undisclosed
Parameters
28B dense
Input price
$0.10 / 1M
Output price
$0.40 / 1M
Cache hit
n/a
Output speed
180 tok/s
Intelligence
33.7（v4.3.2）
Benchmark scores
How it is measured →Bars are scaled to the field maximum for that benchmark.
| Benchmarks | Score | Vs. best in field | Gap |
|---|---|---|---|
| AA Intelligence Index v5 | — | — | not indexed |
| AA Intelligence Index v4.3.2 Intelligence index (legacy) | 33.7 | 59% | −23.9 pts |
| GPQA Diamond | — | — | not indexed |
| Terminal-Bench 4.0 | — | — | not indexed |
| LiveBench Design Document generation (DOCX/PPT/PDF) | 75.9 | 87% | −11.0 pts |
| Vals Index Vals composite index | 40.5 | 55% | −32.6 pts |
Assessment
A 27B dense model under Apache-2.0 with 262K context (extendable to 1M with YaRN). AA v4.3.2 33.7 is the highest score among single-machine deployable models, and its LiveBench design score of 75.9 even beats Gemini 4 Argon's 73.7.
At the same price
The four models closest on blended price, side by side.
| Model | v5 | Blended | tok/s | Score gap |
|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | 36.2 | $0.20 | 235 | — |
| MiniMax M3.1 FlashMiniMax | 29.0 | $0.26 | 118 | — |
| DeepSeek V4.1 Flash Open weightsDeepSeek | 32.5 | $0.53 | 148 | — |
| MiMo-V2.6 Pro Open weightsXiaomi | 30.0 | $0.61 | 81 | — |
Compare side by side
Line it up against other models on price, speed and every benchmark.
The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.
Open the comparison tool → Back to leaderboard