SShogo Bench

Gemini 4 Carbon vs GPT-6.1 Sol

Gemini 4 Carbon leads GPT-6.1 Sol by 3.6 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Gemini 4 Carbon wins 9 and GPT-6.1 Sol wins 2 of 14 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGemini 4 CarbonGPT-6.1 Sol
Agentic coding8280
Long-horizon autonomy8078
Knowledge-work agents6354
Computer use6866
Security & context learning6362

Shared benchmarks

BenchmarkGemini 4 CarbonGPT-6.1 Sol
APEX-Agentsindex84.2%60.0%
Vending-Bench 2index$16,484$12,861
PostTrainBenchindex41.0%38.8%
ARC-AGI98.5%98.5%
ARC-AGI-294.2%94.2%
Chess Puzzles78.0%68.0%
CritPt36.0%31.7%
FrontierMath Tier 495.1%100.0%
FrontierMath Tiers 1-390.5%93.7%
GPQA Diamond96.5%95.4%
OTIS Mock AIME100.0%100.0%
SciCode64.2%55.8%
SimpleBench92.6%82.9%
SimpleQA Verified77.7%73.9%

Specs and price

Gemini 4 CarbonGPT-6.1 Sol
Agent Index73.6 (#2)70 (#5)
Agent $/M$0.84$0.84
Input / output $/M$2.00 / $10.00$2.00 / $10.00
Context1M1.1M
ReleasedNov 10, 2026Sep 29, 2026
WeightsClosedClosed
API hosts56

Don’t pick one. Route.

Shogo can run Gemini 4 Carbon and GPT-6.1 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo