SShogo Bench

Gemini 4 Argon vs Grok 4.7

Gemini 4 Argon leads Grok 4.7 by 14.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 4 Argon wins 20 and Grok 4.7 wins 1 of 21 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 4 ArgonGrok 4.7
Agentic coding7758
Long-horizon autonomy7869
Knowledge-work agents5947
Computer use6139
Security & context learning6150

Shared benchmarks

BenchmarkGemini 4 ArgonGrok 4.7
APEX-Agentsindex82.4%70.0%
Vending-Bench 2index$13,718$10,537
FrontierSWEindex55.0%29.5%
CursorBenchindex52.9%46.3%
ARC-AGI98.5%90.2%
ARC-AGI-291.3%61.4%
Chess Puzzles59.0%41.0%
CritPt27.1%18.0%
DTBench97.6%96.0%
FrontierCode47.5%47.6%
FrontierMath Tier 478.0%17.1%
FrontierMath Tiers 1-386.0%53.0%
GPQA Diamond96.4%92.7%
LMCA63.7%49.4%
MirrorCode58.9%54.4%
OTIS Mock AIME100.0%98.1%
ProofBench99.0%26.0%
SciCode61.8%57.8%
SimpleQA Verified76.0%56.0%
WebDev Arena16801638
WeirdML v320.3%8.5%

Specs and price

Gemini 4 ArgonGrok 4.7
Agent Index69.5 (#6)54.8 (#27)
Agent $/M$0.84$0.98
Input / output $/M$2.00 / $10.00$2.00 / $6.00
Context1M500K
ReleasedOct 13, 2026Sep 21, 2026
WeightsClosedClosed
API hosts55

Don’t pick one. Route.

Shogo can run Gemini 4 Argon 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