SShogo Bench

Grok 4.7 vs Qwen3.8 Max Preview

Grok 4.7 leads Qwen3.8 Max Preview by 1.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Grok 4.7 wins 8 and Qwen3.8 Max Preview wins 7 of 15 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGrok 4.7Qwen3.8 Max Preview
Agentic coding5858
Long-horizon autonomy6963
Knowledge-work agents4746
Computer use3941
Security & context learning5052

Shared benchmarks

BenchmarkGrok 4.7Qwen3.8 Max Preview
APEX-Agentsindex70.0%63.3%
FrontierSWEindex29.5%15.8%
Chess Puzzles41.0%46.0%
CritPt18.0%20.0%
DTBench96.0%92.0%
FrontierMath Tier 417.1%46.3%
FrontierMath Tiers 1-353.0%74.7%
GPQA Diamond92.7%92.7%
LMCA49.4%46.2%
MirrorCode54.4%52.2%
OTIS Mock AIME98.1%99.4%
ProofBench26.0%58.0%
SciCode57.8%53.2%
SimpleQA Verified56.0%45.8%
WebDev Arena16381671

Specs and price

Grok 4.7Qwen3.8 Max Preview
Agent Index54.8 (#27)53.6 (#30)
Agent $/M$0.98Free
Input / output $/M$2.00 / $6.00Free / Free
Context500K1M
ReleasedSep 21, 2026Jul 19, 2026
WeightsClosedClosed
API hosts51

Don’t pick one. Route.

Shogo can run Grok 4.7 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