# Claude Sonnet 4.5 finance AI benchmark results

Every finance benchmark score for Claude Sonnet 4.5 by Anthropic: 3 benchmarks, each with its rank, metric and source date. Scores are never combined across benchmarks.

## Board standings

Claude Sonnet 4.5 is first on 0 benchmarks, top 3 on 1 benchmark, scored on 3 benchmarks. Places on each benchmark's main board with 2 or more models; scores are never combined. https://benchmarks.finance/method/#standings
- Finch: Finance & Accounting Cowork Benchmark: #2 of 2

## Scores

| Benchmark | Rank | Score | Metric | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Market-Bench](https://benchmarks.finance/benchmarks/afterquery-market-bench/) | 6 of 10 | 5126.8 | mean MAE | marketbench.ai leaderboard | date not stated |
| [FinDeepResearch](https://benchmarks.finance/benchmarks/findeepresearch/) | 9 of 10 | 25.8 | overall accuracy score (0-100) | OpenFinArena leaderboard | 15 Oct 2025 |
| [Finch: Finance & Accounting Cowork Benchmark](https://benchmarks.finance/benchmarks/finch/) | 2 of 2 | 25 | workflow pass rate % (human eval) | Paper Table 5 | Apr 2026 |

Source: https://benchmarks.finance/models/claude-sonnet-4-5/

Created and maintained by Moneda.