SShogo Bench

Claude Opus 4.8 vs Gemini 4 Carbon

Gemini 4 Carbon leads Claude Opus 4.8 by 17.3 points on the Shogo Agent Index. Claude Opus 4.8 wins 0 and Gemini 4 Carbon wins 14 of 14 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Gemini 4 Carbon
Agentic coding6382
Long-horizon autonomy6680
Knowledge-work agents4363
Computer use4768
Security & context learning5563

Shared benchmarks

BenchmarkClaude Opus 4.8Gemini 4 Carbon
APEX-Agentsindex48.9%84.2%
Vending-Bench 2index$5,787$16,484
PostTrainBenchindex31.0%41.0%
ARC-AGI92.5%98.5%
ARC-AGI-272.1%94.2%
Chess Puzzles52.0%78.0%
CritPt20.9%36.0%
FrontierMath Tier 456.1%95.1%
FrontierMath Tiers 1-380.0%90.5%
GPQA Diamond91.0%96.5%
OTIS Mock AIME98.3%100.0%
SciCode53.5%64.2%
SimpleBench64.8%92.6%
SimpleQA Verified53.0%77.7%

Specs and price

Claude Opus 4.8Gemini 4 Carbon
Agent Index56.3 (#20)73.6 (#2)
Agent $/M$2.31$0.84
Input / output $/M$5.00 / $25.00$2.00 / $10.00
Context1M1M
ReleasedMay 28, 2026Nov 10, 2026
WeightsClosedClosed
API hosts65

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 and Gemini 4 Carbon side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo