SShogo Bench

Claude Sonnet 5 vs Qwen3.8 Max Preview

Qwen3.8 Max Preview leads Claude Sonnet 5 by 1.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 5 and Qwen3.8 Max Preview wins 10 of 15 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5Qwen3.8 Max Preview
Agentic coding5758
Long-horizon autonomy6563
Knowledge-work agents4346
Computer use4041
Security & context learning5152

Shared benchmarks

BenchmarkClaude Sonnet 5Qwen3.8 Max Preview
APEX-Agentsindex54.5%63.3%
DeepSWEindex53.8%57.5%
Chess Puzzles45.0%46.0%
CritPt16.9%20.0%
DTBench92.5%92.0%
FrontierMath Tier 429.3%46.3%
FrontierMath Tiers 1-365.6%74.7%
GPQA Diamond90.5%92.7%
LMCA50.0%46.2%
MirrorCode63.3%52.2%
OTIS Mock AIME94.7%99.4%
ProofBench77.0%58.0%
SciCode54.3%53.2%
SimpleQA Verified33.7%45.8%
WebDev Arena15371671

Specs and price

Claude Sonnet 5Qwen3.8 Max Preview
Agent Index52.4 (#32)53.6 (#30)
Agent $/M$0.92Free
Input / output $/M$2.00 / $10.00Free / Free
Context1M1M
ReleasedJun 30, 2026Jul 19, 2026
WeightsClosedClosed
API hosts51

Don’t pick one. Route.

Shogo can run Claude Sonnet 5 and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo