# AA-AnalystAgent leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/agentic-aa-analyst-agent

Artificial Analysis AnalystAgent. Every model the catalog carries a published AA-AnalystAgent value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Task success rate |
| Tasks | Spreadsheet and document analysis questions |
| Difficulty | Business and data analysis |
| Published by | [AA-AnalystAgent Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-analyst-agent) |

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.

## AA-AnalystAgent ranking

36 models with a published AA-AnalystAgent value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Task success rate | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | 62.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 60.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 57.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 57.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 56.3 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 53.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 53.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.2 Sol](https://modelscale.dev/models/gpt-6-2-sol) | OpenAI | 53.8 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 52.5 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 51.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 51.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 50.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 50.0 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 48.8 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 48.8 | Observed 2026-11-21 · source benchlm:models |
| 16 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 47.5 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 46.3 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 46.3 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Qwen4 Max](https://modelscale.dev/models/qwen4-max) | Alibaba | 46.3 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 45.0 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 43.8 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Claude Opus 4.7 (Adaptive)](https://modelscale.dev/models/claude-opus-4-7-max) | Anthropic | 43.8 | Last good 2026-11-18 · source benchlm:models |
| 22 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 43.8 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 41.3 | Last good 2026-11-17 · source benchlm:models |
| 25 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 41.3 | Last good 2026-11-17 · source benchlm:models |
| 27 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 38.8 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 38.8 | Last good 2026-10-23 · source benchlm:models |
| 27 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 38.8 | Observed 2026-11-21 · source benchlm:models |
| 30 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | 37.5 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 35.0 | Last good 2026-10-23 · source benchlm:models |
| 32 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 25.0 | Last good 2026-10-23 · source benchlm:models |
| 33 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 23.8 | Last good 2026-10-23 · source benchlm:models |
| 34 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | 12.5 | Last good 2026-10-06 · source benchlm:models |
| 35 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 10.0 | Last good 2026-10-19 · source benchlm:models |
| 36 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 6.3 | Last good 2026-10-08 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
