Atlas

Benchmarks

← All benchmarks

TaxBench Data Retrieval pass^5

Professional Work · 2026-05-04

Data Retrieval subset of TaxBench reporting pass^5 repeated-attempt reliability performance on professional tax tasks.

Top models (higher is better)

ModelScore
GPT-5.5 Pro22.9
GPT-5.520.9
Opus 4.619.2
GPT-5.4 Pro13.5
Gemini 3.1 Pro Preview12.5
Opus 4.711.1
GPT-5.2 Pro7.1
Sonnet 4.67.1
Sonnet 4.56.8
GPT-5.46.0
Grok 4.204.0
Grok 4.1 Fast3.7
GPT-5.22.7
Gemini 3.1 Flash (benchmark label)1.4
Gemini 2.5 Pro1.3
Loading Atlas data…