SShogo Bench

Claude Fable 5 vs Gemini 3.7 Flash

Claude Fable 5 leads Gemini 3.7 Flash by 8.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 17 and Gemini 3.7 Flash wins 3 of 20 shared benchmarks. Gemini 3.7 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5Gemini 3.7 Flash
Agentic coding7461
Long-horizon autonomy6964
Knowledge-work agents5248
Computer use5543
Security & context learning5953

Shared benchmarks

BenchmarkClaude Fable 5Gemini 3.7 Flash
APEX-Agentsindex63.6%67.8%
DeepSWEindex69.9%65.5%
FrontierSWEindex47.0%20.3%
Remote Labor Indexindex16.1%5.0%
ARC-AGI98.5%95.5%
ARC-AGI-289.2%84.6%
Chess Puzzles47.0%66.0%
CritPt28.6%14.3%
DTBench98.4%96.8%
FrontierCode53.5%43.6%
FrontierMath Tier 490.2%36.6%
FrontierMath Tiers 1-387.0%71.6%
GPQA Diamond93.9%94.8%
LMCA61.2%50.4%
MirrorCode70.0%41.1%
OTIS Mock AIME100.0%97.2%
ProofBench95.0%58.0%
SciCode61.0%59.8%
SimpleQA Verified70.7%69.2%
WebDev Arena16281587

Specs and price

Claude Fable 5Gemini 3.7 Flash
Agent Index64.1 (#12)55.7 (#23)
Agent $/M$4.62$0.35
Input / output $/M$10.00 / $50.00$0.75 / $3.75
Context1M1M
ReleasedJun 9, 2026Aug 13, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5 and Gemini 3.7 Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo