SShogo Bench

Claude Fable 5.2 vs GPT-6 Sol

Claude Fable 5.2 leads GPT-6 Sol by 12.8 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 15 and GPT-6 Sol wins 2 of 17 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2GPT-6 Sol
Agentic coding8672
Long-horizon autonomy7876
Knowledge-work agents6748
Computer use7754
Security & context learning6559

Shared benchmarks

BenchmarkClaude Fable 5.2GPT-6 Sol
APEX-Agentsindex80.1%54.3%
Vending-Bench 2index$9,628$14,428
ARC-AGI98.5%95.5%
ARC-AGI-293.8%89.6%
Chess Puzzles79.0%56.0%
CritPt35.7%30.9%
DTBench99.2%97.3%
FrontierMath Tier 4100.0%90.0%
FrontierMath Tiers 1-395.1%89.8%
GPQA Diamond96.0%94.3%
LMCA70.6%59.1%
OTIS Mock AIME99.7%100.0%
ProofBench100.0%83.0%
SciCode67.7%57.6%
SimpleBench94.9%73.1%
SimpleQA Verified94.0%60.7%
WeirdML v343.1%19.7%

Specs and price

Claude Fable 5.2GPT-6 Sol
Agent Index76.4 (#1)63.6 (#13)
Agent $/M$3.21$0.92
Input / output $/M$8.00 / $40.00$2.00 / $10.00
Context1M1.1M
ReleasedNov 9, 2026Sep 22, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 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