# Claude Fable 5.1 vs GPT-6 Astra

Every finance benchmark where both have a score (Anthropic and OpenAI). Data refreshed 2 Nov 2026. Scores from different benchmarks use different scales and are not added up.

| Benchmark | Metric | Claude Fable 5.1 | Claude Fable 5.1 source | GPT-6 Astra | GPT-6 Astra source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| Ramp Accounting Bench | mean reward % (criteria, mean of 3 attempts) (higher is better) | 49.7 | Ramp Labs Accounting Bench, 2 Sept 2026, https://labs.ramp.com/accountingbench | 48.7 | Ramp Labs Accounting Bench, 5 Sept 2026, https://labs.ramp.com/accountingbench | Claude Fable 5.1 |
| Excel Modeling Benchmark (EMB) | accuracy % (v1.1) (higher is better) | 76.7 | Vals.ai leaderboard, 29 Oct 2026, https://www.vals.ai/benchmarks/emb-v1-1 | 72.7 | Vals.ai leaderboard, 29 Oct 2026, https://www.vals.ai/benchmarks/emb-v1-1 | Claude Fable 5.1 |

Source: https://benchmarks.finance/compare/claude-fable-5-1-vs-gpt-6-astra/

Created and maintained by Moneda.