Claude Fable 5 vs Claude Fable 5.2
- Score
- Claude Fable 5 1 · Claude Fable 5.2 18 · 1 tied — higher isn't always better; check the caveats.
- Shared
- 20 benchmarks measured for both models
- Integrity
- 18 of 20 graded A or B
Reported scores — protocols may differ. How we compare
Each bar is drawn on its benchmark's own scale — the ceiling the record states where it has one (of 100), otherwise the best score recorded on that benchmark (rel. 2103). The margin is in points: + is Claude Fable 5, - is Claude Fable 5.2.
Game Playing: Claude Fable 5.2 leads 3–0 across 3 shared game playing benchmarks (largest gap: EBR-bench, 90.48 vs 39.52 — protocols undisclosed).
Reasoning: Claude Fable 5.2 leads 3–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 94 vs 70.7 — protocols undisclosed).
Unknown: Claude Fable 5.2 leads 3–0 across 3 shared unknown benchmarks (largest gap: LMCA, 83.07 vs 71.94 — single evaluator).
Abstract Reasoning: Claude Fable 5.2 leads 1–0 across 2 shared abstract reasoning benchmarks (largest gap: ARC-AGI-2, 93.75 vs 89.17 — protocols undisclosed).
Math: Evenly split 1–1 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 Claude Fable 5.2.
Claude Fable 5.2 leads 18–1 across 20 shared benchmarks. Claude Fable 5 leads 1 benchmark and Claude Fable 5.2 leads 18, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Fable 5 and Claude Fable 5.2 have 20 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Fable 5.2 leads game playing 3–0. Claude Fable 5.2 leads reasoning 3–0.