ModelsCompareBest forBenchmarksStatusPricingAPI

Qwen3.8-Max

Qwen·Pending·Released 2026-08-02textvision
Context1,000k
Max output131.072k
Input / 1M$1.65 ↗
Output / 1M$4.951 ↗
Cached in-
Benchmarks9

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tier 4 v2 (Epoch AI run)#12/4446.3% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#12/5974.7% ↗
GPQA Diamond (Epoch AI run)#15/7792.7% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#5/7699.4% ↗
SimpleQA Verified (Epoch AI run)#24/5345.8% ↗
LMArena Elo#3/621480.6 ↗
GPQA Diamond#12/7092.6% ↗
SWE-Bench Pro#2/1567.7% ↗
Terminal-Bench 2.1#5/1786.6% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Qwen

Qwen3.8 27BQwen3-MaxQwen3-Coder-PlusQwen3 235B-A22BQwen3.8-FlashQwen3.8-Flash-Next

Access Qwen3.8-Max and every other model through one endpoint with automatic failover: Respan gateway.