GPT-6.1 Sol vs Claude Fable 5.1: benchmarks and token cost

This comparison uses GPT-6.1 Sol (Max) and Claude Fable 5.1 (Xhigh, Default Fallback). It reports the captured benchmark data, with no new hands-on test.

Sol and Fable differ materially in captured rates

Sol scores 54.5 on the captured intelligence index and Fable 49.7. Sol’s listed input and output rates are one fifth of Fable’s. Compare quality on the intended task set and preserve the Max and Xhigh configurations in any test. These figures support an evaluation shortlist rather than a claim that an older deployment can be replaced without checking its behavior.

How to read the table

The intelligence index is an aggregate measurement, not a percentage of correct answers in your application. Input and output prices are separate rates per million tokens. Coding and math indices are unavailable in this capture and must not be read as zero. Compare first-token latency separately from output-token throughput, and use the same model effort settings for a trial. Choose using task quality, total time and the cost of accepted results; provider features and deployment requirements need their own checks.