SShogo Bench

Gemini 3.6 Flash vs Grok 4.7

Grok 4.7 leads Gemini 3.6 Flash by 6.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 3.6 Flash wins 7 and Grok 4.7 wins 10 of 17 shared benchmarks. Gemini 3.6 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 3.6 FlashGrok 4.7
Agentic coding5358
Long-horizon autonomy5869
Knowledge-work agents3947
Computer use3739
Security & context learning4950

Shared benchmarks

BenchmarkGemini 3.6 FlashGrok 4.7
APEX-Agentsindex46.9%70.0%
ARC-AGI91.2%90.2%
ARC-AGI-260.4%61.4%
Chess Puzzles42.0%41.0%
CritPt10.6%18.0%
DTBench95.5%96.0%
FrontierCode34.4%47.6%
FrontierMath Tier 422.0%17.1%
FrontierMath Tiers 1-358.9%53.0%
GPQA Diamond94.1%92.7%
LMCA44.9%49.4%
MirrorCode23.3%54.4%
OTIS Mock AIME94.2%98.1%
ProofBench36.0%26.0%
SciCode53.4%57.8%
SimpleQA Verified66.2%56.0%
WebDev Arena15371638

Specs and price

Gemini 3.6 FlashGrok 4.7
Agent Index48.3 (#39)54.8 (#27)
Agent $/M$0.35$0.98
Input / output $/M$0.75 / $3.75$2.00 / $6.00
Context1M500K
ReleasedJul 21, 2026Sep 21, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Gemini 3.6 Flash and Grok 4.7 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo