Verdict
GPT-6.1 Sol leads 10–2 across 14 shared benchmarks.
Claude Fable 5 2 · GPT-6.1 Sol 10 · 2 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-6.1 Sol leads 4–0 across 4 shared unknown benchmarks (largest gap: Furniture Assembly, 71.43 vs 8.33 — protocols undisclosed).
Reasoning: GPT-6.1 Sol leads 2–0 across 3 shared reasoning benchmarks (largest gap: GPQA diamond, 93.86 vs 81.14 — protocols undisclosed).
Math: GPT-6.1 Sol leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 100 vs 90.2 — protocols undisclosed).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Agentic / Tool Use
“The longer and more complex the task, the larger Fable 5's lead over our other models”
Coding
“It is state-of-the-art on nearly all tested benchmarks of AI capability, showing exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas”
General
“Fable 5's capabilities exceed those of any model we've ever made generally available”
Multimodal
“It can extract precise numbers from detailed scientific figures and can perform complex vision-based tasks like rebuilding a web app's source code from screenshots alone”
No vendor claims on file for GPT-6.1 Sol.
GPT-6.1 Sol leads 10–2 across 14 shared benchmarks. Claude Fable 5 leads 2 benchmarks and GPT-6.1 Sol leads 10, with 2 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Fable 5 and GPT-6.1 Sol have 14 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-6.1 Sol leads unknown 4–0. GPT-6.1 Sol leads reasoning 2–0.