SShogo Bench

Claude Fable 5 vs GPT-6.1 Sol

GPT-6.1 Sol leads Claude Fable 5 by 5.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 5 and GPT-6.1 Sol wins 14 of 21 shared benchmarks. GPT-6.1 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5GPT-6.1 Sol
Agentic coding7480
Long-horizon autonomy6978
Knowledge-work agents5254
Computer use5566
Security & context learning5962

Shared benchmarks

BenchmarkClaude Fable 5GPT-6.1 Sol
APEX-Agentsindex63.6%60.0%
Vending-Bench 2index$5,680$12,861
PostTrainBenchindex37.3%38.8%
ARC-AGI98.5%98.5%
ARC-AGI-289.2%94.2%
Chess Puzzles47.0%68.0%
CritPt28.6%31.7%
DTBench98.4%96.5%
FrontierCode53.5%50.2%
FrontierMath Tier 490.2%100.0%
FrontierMath Tiers 1-387.0%93.7%
GPQA Diamond93.9%95.4%
LMCA61.2%62.8%
MirrorCode70.0%61.1%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%99.0%
SciCode61.0%55.8%
SimpleBench81.9%82.9%
SimpleQA Verified70.7%73.9%
WebDev Arena16281759
WeirdML v315.6%38.3%

Specs and price

Claude Fable 5GPT-6.1 Sol
Agent Index64.1 (#12)70 (#5)
Agent $/M$4.62$0.84
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1.1M
ReleasedJun 9, 2026Sep 29, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5 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