PRACTICAL WORKFLOW / 01

Analyse a spreadsheet.

Find patterns, check calculations and turn rows into a clear business answer.

File uploads and code execution depend on the app hosting the model. Verify calculations in Excel or Python.

Three ways to choose.

These are automated capability-based shortlists, not Enterprise DNA tested recommendations. Candidates require text support and at least 32,000 context tokens. Preview, experimental, batch and free variants are excluded. Cost picks require non-zero listed rates. Published index scores are a guide, not proof of task completion.

Published benchmark leader

No matching measurement is available. Explore the catalogue and test a candidate on your own sample.

Lowest estimated API cost

Qwen3 4B ↗

Lowest listed cost for 10,000 input and 2,000 output tokens. Output quality and retries can change the final cost.

Input / 1M tokens: $0.030
Output / 1M tokens: $0.030
Example task estimate: $0.00036 USD
Price record: 2026-07-13

Check source & availability ↗

Fastest measured output

Gemini 2.5 Flash-Lite ↗

Highest recorded output throughput among matching models. App latency and tool time are additional.

Input / 1M tokens: $0.100
Output / 1M tokens: $0.400
Example task estimate: $0.00180 USD
Price record: 2026-07-13

Check source & availability ↗

API estimates exclude caching, tools, reasoning overhead, retries and provider fees. Access through a chat app or subscription has its own pricing and capabilities.

GET A USEFUL RESULT

Your first run.

Use a small, anonymised CSV with known totals.
Ask for calculations, assumptions and row references.
Recalculate the totals before using the conclusion.

A prompt to start with.

Analyse the CSV below. First describe its columns and missing values. Calculate totals and trends using executable Python or spreadsheet formulas, if your environment supports them. Otherwise provide the code for me to run. Separate calculated facts from interpretations. Cite the rows behind each finding and flag anything you cannot verify.

[Paste anonymised CSV and the business question here.]

MAKE YOUR OWN COMPARISON

Same task. Same evidence. Better decision.

Try the same redacted sample and prompt with two models. Record whether each result is correct, how much editing it needs, elapsed time and total cost including retries. Keep the outputs alongside your expected answer. Choose the model that completes your work reliably.

Compare models for this job →