Claude Opus 5 edges out Fable 5 on EyeBench-V3, but still trails GPT and Gemini

adonis_singh · x · 2026-07-25

Claude Opus 5 is reported to beat Claude Fable 5 on EyeBench-V3, becoming the top Anthropic model on that benchmark, though it still trails GPT and Gemini models.

The chart shows Opus 5 at 20.0% correct versus Fable 5 at 19.0%, with OpenAI and Google models ahead on the same benchmark.

Related event: Claude Opus 5 Lags in Vision Benchmarks and Cost Efficiency(4 posts)→

Original post →

More from Models

Models channel →