Claude Fable 5 vs GPT-5.6 Sol on HealthBench Professional
updated August 16, 2026
Claude Fable 5 scores 0.660 to GPT-5.6 Sol's 0.605, a gap of 0.055 on the 525 physician-graded tasks of HealthBench Professional. The table below puts the scores next to what each model costs to actually run.
Side by side
 Claude Fable 5 |  GPT-5.6 Sol | |
|---|---|---|
| score | 0.660 | 0.605 |
| rank | 1 of 9 | 2 of 9 |
| context window | 1.0M | 1.1M |
| price per 1M tokens, in / out | $10.00 / $50.00 | $5.00 / $30.00 |
| 1,000 consult exchanges | $55.00 | $31.00 |
| released | 2026-06-09 | 2026-07-09 |
| license | proprietary | proprietary |
Consult exchange: 2,000 input and 700 output tokens, priced at list rates as of August 16, 2026. GPT-5.6 models charge higher rates above 272K input tokens. MAI-Thinking-1 is in public preview on Microsoft Foundry without final list pricing.
Reading this pairing
This is the flagship pairing, and it is not close by this board's standards: 0.055 is the widest gap between neighboring models in the top seven, and Claude Fable 5 is the only model above 0.61. The lead is priced accordingly. Fable 5 lists at twice Sol's input rate and $20 more per million output tokens, so a high-volume deployment pays roughly double for the last increment of rubric adherence. Where single hard consults matter more than volume, the gap is the point; where volume dominates, Sol is the sensible flagship.
Which scores higher on HealthBench Professional, Claude Fable 5 or GPT-5.6 Sol?
Claude Fable 5 scores higher: 0.660 against GPT-5.6 Sol's 0.605, a difference of 0.055 on the 525-task set, as of August 16, 2026.
Which is cheaper to run, Claude Fable 5 or GPT-5.6 Sol?
GPT-5.6 Sol. 1,000 typical consult exchanges (2,000 input and 700 output tokens each) cost $31.00 against $55.00 at list rates.
Related comparisons
- 0.605 vs 0.598
- 0.660 vs 0.598
Full results for both models: Claude Fable 5 and GPT-5.6 Sol. The complete score-difference matrix is on the compare page.