# Claude Fable 5.1 finance AI benchmark results

Every finance benchmark score for Claude Fable 5.1 by Anthropic: 4 benchmarks, each with its rank, metric and source date. Scores are never combined across benchmarks.

## Board standings

Claude Fable 5.1 is first on 1 benchmark, top 3 on 4 benchmarks, scored on 4 benchmarks. Places on each benchmark's main board with 2 or more models; scores are never combined. https://benchmarks.finance/method/#standings
- Excel Modeling Benchmark (EMB): #1 of 10
- MortgageTax: #2 of 5
- Ramp Accounting Bench: #3 of 5
- Tax Agent Bench: #2 of 10

## Scores

| Benchmark | Rank | Score | Metric | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Excel Modeling Benchmark (EMB)](https://benchmarks.finance/benchmarks/vals-emb/) | 1 of 10 | 76.7 | accuracy % (v1.1) | Vals.ai leaderboard | 29 Oct 2026 |
| [Tax Agent Bench](https://benchmarks.finance/benchmarks/vals-tax-agent-bench/) | 2 of 10 | 49.2 | accuracy % (all-pass x citation factor) | Vals.ai leaderboard | 29 Oct 2026 |
| [MortgageTax](https://benchmarks.finance/benchmarks/vals-mortgage-tax/) | 2 of 5 | 70.8 | accuracy % | Vals.ai MortgageTax leaderboard | 1 Sept 2026 |
| [Ramp Accounting Bench](https://benchmarks.finance/benchmarks/ramp-accounting-bench/) | 3 of 5 | 49.7 | mean reward % (criteria, mean of 3 attempts) | Ramp Labs Accounting Bench | 2 Sept 2026 |

Source: https://benchmarks.finance/models/claude-fable-5-1/

Created and maintained by Moneda.