SShogo Bench

Claude Fable 5.2 vs GPT-5.6 Sol

Claude Fable 5.2 leads GPT-5.6 Sol by 14.6 points on the Shogo Agent Index. Claude Fable 5.2 wins 19 and GPT-5.6 Sol wins 1 of 20 shared benchmarks. GPT-5.6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2GPT-5.6 Sol
Agentic coding8671
Long-horizon autonomy7872
Knowledge-work agents6746
Computer use7753
Security & context learning6558

Shared benchmarks

BenchmarkClaude Fable 5.2GPT-5.6 Sol
APEX-Agentsindex80.1%51.4%
Vending-Bench 2index$9,628$9,619
FrontierSWEindex69.9%32.2%
CursorBenchindex60.0%41.7%
PostTrainBenchindex44.6%31.0%
ARC-AGI98.5%97.5%
ARC-AGI-293.8%92.5%
Chess Puzzles79.0%68.0%
CritPt35.7%32.3%
DTBench99.2%96.0%
FrontierMath Tier 4100.0%82.9%
FrontierMath Tiers 1-395.1%89.1%
GPQA Diamond96.0%93.5%
LMCA70.6%59.2%
OTIS Mock AIME99.7%100.0%
ProofBench100.0%83.0%
SciCode67.7%57.8%
SimpleBench94.9%71.7%
SimpleQA Verified94.0%69.7%
WeirdML v343.1%15.0%

Specs and price

Claude Fable 5.2GPT-5.6 Sol
Agent Index76.4 (#1)61.8 (#14)
Agent $/M$3.21$1.85
Input / output $/M$8.00 / $40.00$4.00 / $20.00
Context1M1.1M
ReleasedNov 9, 2026Aug 7, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and GPT-5.6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo