SShogo Bench

Claude Fable 5 vs GPT-6 Sol

Claude Fable 5 leads GPT-6 Sol by 0.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 11 and GPT-6 Sol wins 8 of 20 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5GPT-6 Sol
Agentic coding7472
Long-horizon autonomy6976
Knowledge-work agents5248
Computer use5554
Security & context learning5959

Shared benchmarks

BenchmarkClaude Fable 5GPT-6 Sol
APEX-Agentsindex63.6%54.3%
Vending-Bench 2index$5,680$14,428
ARC-AGI98.5%95.5%
ARC-AGI-289.2%89.6%
Chess Puzzles47.0%56.0%
CritPt28.6%30.9%
DTBench98.4%97.3%
FrontierCode53.5%49.3%
FrontierMath Tier 490.2%90.0%
FrontierMath Tiers 1-387.0%89.8%
GPQA Diamond93.9%94.3%
LMCA61.2%59.1%
MirrorCode70.0%48.9%
OTIS Mock AIME100.0%100.0%
ProofBench95.0%83.0%
SciCode61.0%57.6%
SimpleBench81.9%73.1%
SimpleQA Verified70.7%60.7%
WebDev Arena16281689
WeirdML v315.6%19.7%

Specs and price

Claude Fable 5GPT-6 Sol
Agent Index64.1 (#12)63.6 (#13)
Agent $/M$4.62$0.92
Input / output $/M$10.00 / $50.00$2.00 / $10.00
Context1M1.1M
ReleasedJun 9, 2026Sep 22, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5 and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo