SShogo Bench

Claude Fable 5.1 vs Gemini 4 Carbon

Gemini 4 Carbon leads Claude Fable 5.1 by 5.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.1 wins 1 and Gemini 4 Carbon wins 13 of 15 shared benchmarks. Gemini 4 Carbon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1Gemini 4 Carbon
Agentic coding8082
Long-horizon autonomy7180
Knowledge-work agents5563
Computer use6268
Security & context learning6163

Shared benchmarks

BenchmarkClaude Fable 5.1Gemini 4 Carbon
APEX-Agentsindex68.6%84.2%
Vending-Bench 2index$5,422$16,484
FrontierSWEindex56.3%61.2%
CursorBenchindex51.8%60.4%
PostTrainBenchindex44.6%41.0%
ARC-AGI97.5%98.5%
ARC-AGI-290.0%94.2%
Chess Puzzles48.0%78.0%
CritPt31.1%36.0%
FrontierMath Tier 487.8%95.1%
FrontierMath Tiers 1-390.2%90.5%
OTIS Mock AIME100.0%100.0%
SciCode63.1%64.2%
SimpleBench86.6%92.6%
SimpleQA Verified70.8%77.7%

Specs and price

Claude Fable 5.1Gemini 4 Carbon
Agent Index68.2 (#10)73.6 (#2)
Agent $/M$4.01$0.84
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1M
ReleasedSep 1, 2026Nov 10, 2026
WeightsClosedClosed
API hosts35

Don’t pick one. Route.

Shogo can run Claude Fable 5.1 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