0

Qwen3.8 Max

Publisher
Alibaba
Context
1M
Input
Output
Released
3 Aug 2026

Cite

Notes

Only stored in your browser.

Attribution

Benchmark scores
AAVals AILech Mazur
Attribution policy →
Context
1M
Input
$2
/1M tok
Output
$6
/1M tok
Blended
$3
#425/ 494/1M · 3:1
Speed
39
#94/ 493tok/s
Cache read
$0.25
0.13x input
Cache write
$2.50
1.25x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reasoning effortIndexSpeed
Default40.20 t/s
090245.439 t/s

Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers

Reported on 15 evals across 9 domains - best 92.7% on GPQA Diamond · #18 of 511

Reported eval scores

15
GPQA Diamond92.7
SciCode53.2
Humanity's Last Exam (HLE)43
Vals Index48.3
TaxEval v275.6
CorpFin v265.9
Finance Agent (v2)50.6
MortgageTax64
SAGE51.3
ProofBench58
MedScribe84.9
MedCode40.7
Vals Multimodal Index65.4
Vibe Code Bench v1.164.7
Creative Story-Writing Benchmark53