SShogo Bench

Gemini 3.6 Flash vs Qwen3.8 Max Preview

Qwen3.8 Max Preview leads Gemini 3.6 Flash by 5.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.6 Flash wins 4 and Qwen3.8 Max Preview wins 11 of 15 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.6 FlashQwen3.8 Max Preview
Agentic coding5358
Long-horizon autonomy5863
Knowledge-work agents3946
Computer use3741
Security & context learning4952

Shared benchmarks

BenchmarkGemini 3.6 FlashQwen3.8 Max Preview
APEX-Agentsindex46.9%63.3%
DeepSWEindex46.7%57.5%
Chess Puzzles42.0%46.0%
CritPt10.6%20.0%
DTBench95.5%92.0%
FrontierMath Tier 422.0%46.3%
FrontierMath Tiers 1-358.9%74.7%
GPQA Diamond94.1%92.7%
LMCA44.9%46.2%
MirrorCode23.3%52.2%
OTIS Mock AIME94.2%99.4%
ProofBench36.0%58.0%
SciCode53.4%53.2%
SimpleQA Verified66.2%45.8%
WebDev Arena15371671

Specs and price

Gemini 3.6 FlashQwen3.8 Max Preview
Agent Index48.3 (#39)53.6 (#30)
Agent $/M$0.35Free
Input / output $/M$0.75 / $3.75Free / Free
Context1M1M
ReleasedJul 21, 2026Jul 19, 2026
WeightsClosedClosed
API hosts61

Don’t pick one. Route.

Shogo can run Gemini 3.6 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