SShogo Bench

DeepSeek V4.1 Flash vs Qwen3.8 Max Preview

Qwen3.8 Max Preview leads DeepSeek V4.1 Flash by 2.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash wins 3 and Qwen3.8 Max Preview wins 11 of 14 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarDeepSeek V4.1 FlashQwen3.8 Max Preview
Agentic coding5758
Long-horizon autonomy6263
Knowledge-work agents3946
Computer use4041
Security & context learning5152

Shared benchmarks

BenchmarkDeepSeek V4.1 FlashQwen3.8 Max Preview
APEX-Agentsindex39.5%63.3%
Chess Puzzles48.0%46.0%
CritPt14.3%20.0%
DTBench89.9%92.0%
FrontierMath Tier 426.8%46.3%
FrontierMath Tiers 1-367.4%74.7%
GPQA Diamond89.8%92.7%
LMCA47.0%46.2%
MirrorCode64.4%52.2%
OTIS Mock AIME98.3%99.4%
ProofBench54.0%58.0%
SciCode51.9%53.2%
SimpleQA Verified42.9%45.8%
WebDev Arena16141671

Specs and price

DeepSeek V4.1 FlashQwen3.8 Max Preview
Agent Index51.2 (#35)53.6 (#30)
Agent $/M$0.12Free
Input / output $/M$0.30 / $1.20Free / Free
Context1M1M
ReleasedSep 10, 2026Jul 19, 2026
WeightsOpenClosed
API hosts391

Don’t pick one. Route.

Shogo can run DeepSeek V4.1 Flash 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