TaxCalcBench: evaluating frontier models on the tax calculation task

Note: this repo has drifted since the original TaxCalcBench paper was published as we’ve benchmarked additional models. If you’d like to see the repo at its state as of the paper release, see the repo as of this commit.

Update: (v2) Tax Year 2025 edition

As of Jun 2026, we’ve released v2 of TaxCalcBench for Tax Year (TY) 2025 with the following features:

• Inputs (e.g. W-2s, 1099s, etc.) are realistic PDFs
• The cases cover state returns in addition to federal returns
• The cases cover much more complex tax/financial situations

Leaderboard

[!TIP] These results are also available as an interactive leaderboard at TaxCalcBench.ai.

Tax Year (TY) 2025

| Model | Correct returns (strict) | Correct returns (lenient) | Correct (by line) | Correct (by line, lenient) | Cost per return | Time per return | | ------------------------------------------ | ---------------------------: |…