Best AI models for data analysis.
334 available models considered · 42 with comparable evidence
Data work can mean extracting a few fields, writing a query or explaining a pattern in a table. This shortlist emphasizes data analysis, mathematics and reasoning. Choose a model around the decisions it must make, then check the output against the original data.
For a balanced task, the current best measured match is GPT-6 Astra at 86.3/100 task fit. Change the difficulty or add requirements in the finder.
Choose task difficulty
Change the range
Quick tasks
Extract known fields, label a small set of records or explain a simple table.
Open finder →Default range
Balanced
Write a query, transform messy records or interpret a calculation with clear assumptions.
Open finder →Change the range
Complex tasks
Investigate inconsistent data, compare competing explanations or design an analysis spanning several sources.
Open finder →Balanced task range
Best measured matches
Task fit applies the published weights for data analysis. Price helps choose a provider after capability; it does not raise a weaker model into this range.
Task fit
86.3 / 100
Capability 82.2/100
Task fit
82.2 / 100
Capability 81.1/100
Lowest eligible listed rate
$0.0422 in · $0.0844 out / M tokens
TrustedRouter ↗Price checked 22 Sept 2026
Measured as deepseek-v4.1-flash-max · max effort. Source ↗
- Claude Fable 5.1 ↗
Anthropic
Task fit
85.4 / 100
Capability 83.4/100
Lowest eligible listed rate
$10 in · $50 out / M tokens
Amazon Bedrock ↗Price checked 22 Sept 2026
Measured as claude-fable-5-1-max-effort · max effort. Source ↗
- Claude Fable 5 ↗
Anthropic
Task fit
85.3 / 100
Capability 83/100
Lowest eligible listed rate
$10 in · $50 out / M tokens
Amazon Bedrock ↗Price checked 22 Sept 2026
Measured as claude-fable-5-max-effort · max effort. Source ↗
- Muse Spark 1.3 ↗
Meta
Task fit
84.8 / 100
Capability 81.6/100
- GPT-5.6 Sol ↗
OpenAI
Task fit
84.7 / 100
Capability 81.1/100
Lowest eligible listed rate
$2 in · $10 out / M tokens
Nous Portal ↗Price checked 22 Sept 2026
Measured as gpt-5.6-sol-max · max effort. Source ↗
- GPT-5.5 ↗
OpenAI
Task fit
84.5 / 100
Capability 80.2/100
- GPT-5.4 ↗
OpenAI
Task fit
82.5 / 100
Capability 78/100
- GPT-5.6 Terra ↗
OpenAI
Task fit
82.4 / 100
Capability 77.9/100
Lowest eligible listed rate
$2 in · $12 out / M tokens
Atlas Cloud ↗Price checked 22 Sept 2026
Measured as gpt-5.6-terra-max · max effort. Source ↗
- Muse Spark 1.2 ↗
Meta
Task fit
81.9 / 100
Capability 78/100
How to read this guide
Benchmark results do not verify the calculations or conclusions in your output. They also do not guarantee spreadsheet access, code execution or reliable extraction from every document layout.
The recommendations use the same Balanced settings as the interactive finder. See the Capability methodology for sources, exact identity rules, task weights and difficulty ranges.