Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Artificial Analysis AutomationBench (AA AutomationBench)

An independently evaluated automation benchmark from Artificial Analysis.

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on AA AutomationBench — September 15, 2026

We mirror the published score view for AA AutomationBench. DeepSeek V4.1 Flash leads the public snapshot at 68.9%, followed by GPT-6 Astra (68.5%) and Grok 4.6 (66.7%). We do not use these results to rank models overall.

1Open weights

DeepSeek V4.1 Flash

DeepSeek

68.9%
Context 1M
2Proprietary

GPT-6 Astra

OpenAI

68.5%
Overall 82.94Context 1.05M
3Proprietary

Grok 4.6

xAI

66.7%
Overall 69.9Context 500K

14 modelsAgenticCurrentDisplay onlyUpdated September 15, 2026

Benchmark score table (14 models)

Score
1
DeepSeek V4.1 FlashDeepSeek · Open weight
68.9%
2
GPT-6 AstraOpenAI · Closed
68.5%
3
Grok 4.6xAI · Closed
66.7%
4
GLM-5.3Z.AI · Open weight
62.2%
5
GLM-5.3-FlashZ.AI · Open weight
60.4%
6
GPT-5.6 SolOpenAI · Closed
60.1%
7
Gemini 3.8 FlashGoogle · Closed
59.9%
8
GPT-5.6 TerraOpenAI · Closed
59.6%
9
Claude Fable 5.1Anthropic · Closed
59.4%
10
Kimi K3Moonshot AI · Closed
58.3%
11
Muse Spark 1.3Meta · Closed
57.9%
12
DeepSeek V4 Pro 0813DeepSeek · Closed
56.7%
13
Claude Opus 5Anthropic · Closed
56.6%
14
Claude Fable 5Anthropic · Closed
54.1%

The published AA AutomationBench snapshot places DeepSeek V4.1 Flash first at 68.9%. The third row is 2.2 points behind. The broader top-10 range is 10.6 points, so the table still separates the published systems.

14 models have been evaluated on AA AutomationBench. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. AA AutomationBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AA AutomationBench

Year

2026

Tasks

Business-process automation tasks

Format

Task success rate

Difficulty

Agentic automation

Stored as a display-only agentic row.

Artificial Analysis AutomationBench Benchmark Leaderboard

BenchLM freshness & provenance

Version

AA AutomationBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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.

FAQ

What does AA AutomationBench measure?

An independently evaluated automation benchmark from Artificial Analysis.

Which model scores highest on AA AutomationBench?

DeepSeek V4.1 Flash by DeepSeek currently leads with a score of 68.9% on AA AutomationBench.

How many models are evaluated on AA AutomationBench?

14 AI models have been evaluated on AA AutomationBench on BenchLM.

Compare Top Models on AA AutomationBench

DeepSeek V4.1 Flash vs GPT-6 AstraGPT-6 Astra vs Grok 4.6Grok 4.6 vs GLM-5.3GLM-5.3 vs GLM-5.3-Flash
Last updated: September 15, 2026 · BenchLM version AA AutomationBench 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.