SShogo Bench

Claude Fable 5 vs Gemini 4 Argon

Gemini 4 Argon leads Claude Fable 5 by 5.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 6 and Gemini 4 Argon wins 15 of 23 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Gemini 4 Argon
Agentic coding7477
Long-horizon autonomy6978
Knowledge-work agents5259
Computer use5561
Security & context learning5961

Shared benchmarks

BenchmarkClaude Fable 5Gemini 4 Argon
APEX-Agentsindex63.6%82.4%
Vending-Bench 2index$5,680$13,718
FrontierSWEindex47.0%55.0%
Remote Labor Indexindex16.1%17.1%
PostTrainBenchindex37.3%40.4%
ARC-AGI98.5%98.5%
ARC-AGI-289.2%91.3%
Chess Puzzles47.0%59.0%
CritPt28.6%27.1%
DTBench98.4%97.6%
FrontierCode53.5%47.5%
FrontierMath Tier 490.2%78.0%
FrontierMath Tiers 1-387.0%86.0%
GPQA Diamond93.9%96.4%
LMCA61.2%63.7%
MirrorCode70.0%58.9%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%99.0%
SciCode61.0%61.8%
SimpleBench81.9%91.7%
SimpleQA Verified70.7%76.0%
WebDev Arena16281680
WeirdML v315.6%20.3%

Specs and price

Claude Fable 5Gemini 4 Argon
Agent Index64.1 (#12)69.5 (#6)
Agent $/M$4.62$0.84
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1M
ReleasedJun 9, 2026Oct 13, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Gemini 4 Argon side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo