SShogo Bench

Gemini 4 Carbon vs Grok 4.6

Gemini 4 Carbon leads Grok 4.6 by 17.4 points on the Shogo Agent Index. Gemini 4 Carbon wins 15 and Grok 4.6 wins 0 of 15 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 4 CarbonGrok 4.6
Agentic coding8261
Long-horizon autonomy8068
Knowledge-work agents6347
Computer use6842
Security & context learning6352

Shared benchmarks

BenchmarkGemini 4 CarbonGrok 4.6
APEX-Agentsindex84.2%65.3%
Vending-Bench 2index$16,484$9,047
FrontierSWEindex61.2%25.3%
CursorBenchindex60.4%41.4%
ARC-AGI98.5%87.5%
ARC-AGI-294.2%67.1%
Chess Puzzles78.0%33.0%
CritPt36.0%19.7%
FrontierMath Tier 495.1%31.7%
FrontierMath Tiers 1-390.5%66.0%
GPQA Diamond96.5%94.0%
OTIS Mock AIME100.0%99.2%
SciCode64.2%56.5%
SimpleBench92.6%75.9%
SimpleQA Verified77.7%49.3%

Specs and price

Gemini 4 CarbonGrok 4.6
Agent Index73.6 (#2)56.2 (#22)
Agent $/M$0.84$0.98
Input / output $/M$2.00 / $10.00$2.00 / $6.00
Context1M500K
ReleasedNov 10, 2026Aug 12, 2026
WeightsClosedClosed
API hosts54

Don’t pick one. Route.

Shogo can run Gemini 4 Carbon and Grok 4.6 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo