Skip to content
Bencher

TestsBenchmarks · Agentic

AA Analyst Agent

Artificial Analysis agentic data-analyst tasks (pass@1).

% solvedHigher is betterCounts toward:Weights: Research & analysis ×0.5The test's websiteOfficial page ↗

The best 14 · 14 models tested

Top 14 · best setting per model · 14 models, 14 results (14 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported
AA Analyst Agent leaderboard
Thinking levelSetting
1Gemini 3.7 FlashGoogle (Gemini / DeepMind)60.0%HighGemini 3.7 Flash (High)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
2Claude Fable 5.1Anthropic57.5%MaxClaude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
3Claude Opus 5Anthropic53.8%MaxClaude Opus 5 (Adaptive Reasoning, Max Effort)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
4GPT-6 AstraOpenAI51.3%MaxGPT-6 Astra (Max)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
5GPT-5.5OpenAI50.0%Extra highGPT-5.5 (Xhigh)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
6Claude Fable 5Anthropic48.8%MaxClaude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
7GPT-5.6 SolOpenAI47.5%MaxGPT-5.6 Sol (Max)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
8Qwen3.8 Max (0902)Qwen (Alibaba)45.0%DefaultQwen3.8 Max (0902)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
9Kimi K3Moonshot AI (Kimi)38.8%MaxKimi K3 (Max)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
10Step 5 PreviewStepFun35.0%DefaultStep 5 PreviewIndependent testIndependentArtificial Analysis ↗—1 Oct 2026
11InklingThinking Machines Lab23.8%Extra highInkling (Xhigh)Independent testIndependentArtificial Analysis ↗—1 Oct 2026
12Mistral Medium 3.5Mistral AI12.5%DefaultMistral Medium 3.5Independent testIndependentArtificial Analysis ↗—1 Oct 2026
13MiniMax M3MiniMax10.0%DefaultMiniMax-M3Independent testIndependentArtificial Analysis ↗—1 Oct 2026
14Nemotron 3 UltraNVIDIA6.3%DefaultNemotron 3 Ultra 550B A55B (Reasoning)Independent testIndependentArtificial Analysis ↗—1 Oct 2026