Artificial Analysis AnalystAgent (AA-AnalystAgent)
We show this table for reference; we do not rank on it.
Artificial Analysis' data-analysis benchmark, testing agents on spreadsheet and document work to answer the quantitative questions a business or data analyst faces day to day.
Benchmark score on AA-AnalystAgent — November 13, 2026
We compile the AA-AnalystAgent rows from secondary reports. Gemini 3.7 Flash leads the table at 60.0%, followed by Claude Fable 5.1 (57.5%) and Claude Sonnet 5.5 (57.5%). We do not use these results to rank models overall.
Gemini 3.7 Flash
Claude Fable 5.1
Anthropic
Carried from an upstream pageClaude Sonnet 5.5
Anthropic
Carried from an upstream page26 modelsAgenticCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (26 models)
None of the 26 results on this page has a documented run by the benchmark or an independent evaluator: 26 carried from an upstream page, where who ran them is not recorded.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Gemini 3.7 FlashGoogleCarried from an upstream page | 60.0% | Carried from an upstream page | Not reported | Closed |
| 2 | Claude Fable 5.1AnthropicCarried from an upstream page | 57.5% | Carried from an upstream page | Not reported | Closed |
| 3 | Claude Sonnet 5.5AnthropicCarried from an upstream page | 57.5% | Carried from an upstream page | Not reported | Closed |
| 4 | Claude Opus 5.5AnthropicCarried from an upstream page | 56.3% | Carried from an upstream page | Not reported | Closed |
| 5 | Claude Opus 5AnthropicCarried from an upstream page | 53.8% | Carried from an upstream page | Not reported | Closed |
| 6 | Claude Haiku 5.5AnthropicCarried from an upstream page | 53.8% | Carried from an upstream page | Not reported | Closed |
| 7 | Grok 4.7xAICarried from an upstream page | 52.5% | Carried from an upstream page | Not reported | Closed |
| 8 | GPT-6 AstraOpenAICarried from an upstream page | 51.2% | Carried from an upstream page | Not reported | Closed |
| 9 | Inkling 2 SmallThinking Machines LabCarried from an upstream page | 51.2% | Carried from an upstream page | Not reported | Closed |
| 10 | GPT-5.5OpenAICarried from an upstream page | 50.0% | Carried from an upstream page | Not reported | Closed |
| 11 | GPT-6.1 SolOpenAICarried from an upstream page | 50.0% | Carried from an upstream page | Not reported | Closed |
| 12 | Claude Fable 5AnthropicCarried from an upstream page | 48.8% | Carried from an upstream page | Not reported | Closed |
| 13 | Gemini 4 ArgonGoogleCarried from an upstream page | 48.8% | Carried from an upstream page | Not reported | Closed |
| 14 | GPT-5.6 SolOpenAICarried from an upstream page | 47.5% | Carried from an upstream page | Not reported | Closed |
| 15 | Claude Sonnet 5AnthropicCarried from an upstream page | 46.3% | Carried from an upstream page | Not reported | Closed |
| 16 | Gemini 3.8 FlashGoogleCarried from an upstream page | 46.3% | Carried from an upstream page | Not reported | Closed |
| 17 | Claude Opus 4.8AnthropicCarried from an upstream page | 45.0% | Carried from an upstream page | Not reported | Closed |
| 18 | Gemini 3.5 FlashGoogleCarried from an upstream page | 45.0% | Carried from an upstream page | Not reported | Closed |
| 19 | Claude Opus 4.7 (Adaptive)AnthropicCarried from an upstream page | 43.8% | Carried from an upstream page | Not reported | Closed |
| 20 | GPT-6 LunaOpenAICarried from an upstream page | 43.8% | Carried from an upstream page | Not reported | Closed |
| 21 | Gemini 3.1 ProGoogleCarried from an upstream page | 41.3% | Carried from an upstream page | Not reported | Closed |
| 22 | Grok 4.6xAICarried from an upstream page | 41.3% | Carried from an upstream page | Not reported | Closed |
| 23 | Kimi K3Moonshot AICarried from an upstream page | 38.8% | Carried from an upstream page | Not reported | Open |
| 24 | Kimi K3.1 ProMoonshot AICarried from an upstream page | 38.8% | Carried from an upstream page | Not reported | Open |
| 25 | GLM-5.3Z.AICarried from an upstream page | 38.8% | Carried from an upstream page | Not reported | Open |
| 26 | MiMo-V2.6-ProXiaomiCarried from an upstream page | 37.5% | Carried from an upstream page | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Among the reported AA-AnalystAgent rows, Gemini 3.7 Flash is first at 60.0%. The third row is 2.5 points behind. The broader top-10 range is 10.0 points, so the table still separates the published systems.
26 models have been evaluated on AA-AnalystAgent. The benchmark falls in the Agentic category. AA-AnalystAgent is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About AA-AnalystAgent
Year
2026
Tasks
Spreadsheet and document analysis questions
Format
Task success rate
Difficulty
Business and data analysis
Private dataset, independently run by Artificial Analysis. Display-only; not yet admitted as independent-run evidence.
Freshness and provenance
Version
AA-AnalystAgent 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does AA-AnalystAgent measure?
Artificial Analysis' data-analysis benchmark, testing agents on spreadsheet and document work to answer the quantitative questions a business or data analyst faces day to day.
Which model scores highest on AA-AnalystAgent?
Gemini 3.7 Flash by Google currently leads with a score of 60.0% on AA-AnalystAgent.
How many models are evaluated on AA-AnalystAgent?
26 AI models have published results on AA-AnalystAgent in the BenchLM catalog.
Compare top models on AA-AnalystAgent
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.