Accuracy benchmark
OfficeQA Pro, Databricks' benchmark for grounded reasoning over documents.
- corpus
- 1,435 U.S. Treasury documents · 90 questions
- scoring
- exact match
Results
- 1 Supermodel + Claude Opus 5.5
- 2 Mixedbread Toast + GPT-5.6 Sol
- 3 Databricks Genie + Claude Fable 5
- 4 Snowflake Cortex Agent
- 5 Claude Opus 5.5 alone
- 6 GPT Astra
- 7 Claude Code + Claude Fable 5
- 8 Codex + GPT-5.6 Sol
- 9 Claude Code + Claude Sonnet 5
Cost and time per question
- 1 Supermodel + Claude Opus 5.5 accuracy: 73.3%
- 2 Mixedbread Toast + GPT-5.6 Sol accuracy: 70.0%
- 3 Databricks Genie + Claude Fable 5 accuracy: 60.0%
- 4 Codex + GPT-5.6 Sol accuracy: 33.3%
- 5 Claude Code + Claude Sonnet 5 accuracy: 15.6%
- 6 Claude Code + Claude Fable 5 accuracy: 45.6%
- 1 Supermodel + Claude Opus 5.5 accuracy: 73.3%
- 2 Claude Opus 5.5 alone accuracy: 55.6%
- 3 GPT Astra accuracy: 49.6%
Questions
What is Supermodel?
Small models that run next to your data and pass the frontier model only what matters.
How much does Supermodel add to the same model?
Claude Opus 5.5 scores 55.6% on its own and 73.3% with Supermodel, 17.7 points higher, in 74 seconds a question against 156.
Why is Snowflake Cortex Agent missing from the cost board?
Its accuracy, 57.8%, is the only figure we have for it, so it is ranked on accuracy alone.
infino init
#1 in accuracy. Try it on your own data.
or run it yourself: pip install infino · Apache-2.0 · quickstart →