Artificial Analysis · Intelligence Index · XhighBenchmarks, as Artificial Analysis ran them- 91%GPQA Diamond
- 34%Humanity's Last Exam
- 6%Terminal-Bench 4.0
- 80%Terminal-Bench 2.1
- 47%SciCode
- 48%τ²-Bench Banking
- 82%Long context reasoning
- Speed
- 37.7 tokens/s
- First answer
- 1.5 s
- thinking included
- Per 1M tokens
- $0.50 in · $3.00 out
- Context
- 1M tokens
LMArena · Text100thof 417· 23rd of 227 open models
Rated by versionQwenRated 44 points above Qwen3.5-35B-A3B.
Qwen3.8-27B · 1,438 (1,433–1,443) · 100th
Against list priceRating for the price
Qwen3.8-27B · 1,438 · $0.37 per 1M tokens ($0.04 in, $1.35 out) · 1M context
Qwen3.8-27B · 1,438 · $0.37 per 1M tokens ($0.04 in, $1.35 out) · 1M context
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 22 October 2026 · Artificial Analysis, read 22 October 2026
Qwen3.8-27B