Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM

Artificial Analysis Agentic Index (AA Agentic Index)

A display-only Artificial Analysis agentic index.

Data verified 31 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on AA Agentic Index — September 10, 2026

We mirror the published score view for AA Agentic Index. Claude Fable 5.1 leads the public snapshot at 58.0%, followed by Claude Opus 5 (56.2%) and Muse Spark 1.3 (55.7%). We do not use these results to rank models overall.

1Proprietary

Claude Fable 5.1

Anthropic

58.0%
Overall 84.61Context 1M
2Proprietary

Claude Opus 5

Anthropic

56.2%
Overall 81.97
3Proprietary

Muse Spark 1.3

Meta

55.7%
Context 1M

82 modelsAgenticCurrentDisplay onlyUpdated September 10, 2026

Benchmark score table (82 models)

Score
1
Claude Fable 5.1Anthropic · Closed
58.0%
2
Claude Opus 5Anthropic · Closed
56.2%
3
Muse Spark 1.3Meta · Closed
55.7%
4
GLM-5.3Z.AI · Open weight
53.4%
5
Grok 4.6xAI · Closed
53.4%
6
GPT-6 AstraOpenAI · Closed
51.5%
7
Claude Fable 5Anthropic · Closed
51.0%
8
Kimi K3Moonshot AI · Closed
50.6%
9
GPT-5.6 SolOpenAI · Closed
50.5%
10
Qwen3.8 Max PreviewAlibaba · Closed
49.6%
11
DeepSeek V4 Pro 0813DeepSeek · Closed
49.6%
12
Qwen3.8-27BAlibaba · Open weight
46.5%
13
Claude Sonnet 5Anthropic · Closed
44.3%
14
Muse Spark 1.2Meta · Closed
44.0%
15
GPT-5.6 TerraOpenAI · Closed
43.7%
16
GPT-5.6 LunaOpenAI · Closed
42.7%
17
Claude Opus 4.8Anthropic · Closed
42.6%
18
Grok 4.5xAI · Closed
42.1%
19
DeepSeek V4 Flash 0731DeepSeek · Closed
41.7%
20
Gemini 3.8 FlashGoogle · Closed
41.1%
21
Claude Opus 4.7 (Adaptive)Anthropic · Closed
39.5%
22
GLM-5.2Z.AI · Open weight
39.4%
23
GPT-5.5OpenAI · Closed
37.3%
24
Gemini 3.7 FlashGoogle · Closed
36.4%
25
DeepSeek V4 Pro (High)DeepSeek · Open weight
35.3%
26
Quasar 438BMultiverse Computing · Closed
32.7%
27
MiniMax M3MiniMax · Open weight
30.8%
28
Gemini 3.6 FlashGoogle · Closed
30.1%
29
Muse Spark 1.1Meta · Closed
27.5%
30
Gemini 3.5 FlashGoogle · Closed
27.3%
31
Hy3Tencent · Open weight
25.6%
32
Hy3 PreviewTencent · Open weight
25.6%
33
GLM-5.1Z.AI · Open weight
25.2%
34
Inkling-SmallThinking Machines Lab · Open weight
24.9%
35
InklingThinking Machines Lab · Open weight
24.3%
36
Qwen3.7 MaxAlibaba · Closed
23.9%
37
MiMo-V2.5-ProXiaomi · Closed
22.7%
38
Kimi K2.7 CodeMoonshot AI · Open weight
22.5%
39
Kimi K2.6Moonshot AI · Open weight
22.1%
40
Nemotron 3 UltraNVIDIA · Open weight
21.7%
41
Ling 3.0 FlashInclusionAI · Open weight
21.0%
42
Ling 3.0 Flash FP8InclusionAI · Open weight
21.0%
43
Qwen3.6-27BAlibaba · Open weight
20.1%
44
Qwen3.7 PlusAlibaba · Closed
19.7%
45
GPT-5.4 miniOpenAI · Closed
19.6%
46
GPT-5.4 nanoOpenAI · Closed
17.7%
47
Grok 4.3xAI · Closed
17.2%
48
MiniMax M2.7MiniMax · Open weight
16.8%
49
Gemini 3.5 Flash-LiteGoogle · Closed
15.9%
50
Qwen3.6-35B-A3BAlibaba · Open weight
15.0%
51
Muse Glimmer 30BMeta · Open weight
10.5%
52
Gemini 3.1 ProGoogle · Closed
10.3%
53
Qwen3.5-122B-A10BAlibaba · Open weight
9.6%
54
Mistral Medium 3.5 128BMistral · Open weight
9.3%
55
GPT-5 miniOpenAI · Closed
8.9%
56
Gemma 4 31BGoogle · Open weight
6.7%
57
GPT-OSS 120BOpenAI · Open weight
6.2%
58
Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open weight
6.1%
59
Nemotron 3 Super 100BNVIDIA · Open weight
4.1%
60
Nemotron 3 Super 120B A12BNVIDIA · Open weight
4.1%
61
Mercury 2Inception · Closed
4.0%
62
Granite 4.2 8BIBM · Open weight
3.7%
63
Command A+Cohere · Open weight
3.6%
64
Gemini 2.5 ProGoogle · Closed
3.5%
65
Mistral Large 3Mistral · Closed
2.4%
66
Mistral Small 4Mistral · Open weight
1.4%
67
Mistral Small 4 (Reasoning)Mistral · Open weight
1.4%
68
GPT-OSS 20BOpenAI · Open weight
1.4%
69
Trinity-Large-ThinkingArcee AI · Open weight
1.2%
70
Trinity-Large-PreviewArcee AI · Open weight
1.2%
71
Ministral 3 14B (Reasoning)Mistral · Open weight
1.1%
72
Ministral 3 14BMistral · Open weight
1.1%
73
Nemotron 3 Nano 30BNVIDIA · Open weight
1.0%
74
DeepSeek V3DeepSeek · Open weight
0.8%
75
Ministral 3 3B (Reasoning)Mistral · Open weight
0.8%
76
Ministral 3 3BMistral · Open weight
0.8%
77
Celeris-1Celeris · Closed
0.7%
78
Llama 4 MaverickMeta · Open weight
0.6%
79
Ministral 3 8B (Reasoning)Mistral · Open weight
0.6%
80
Ministral 3 8BMistral · Open weight
0.6%
81
Llama 4 ScoutMeta · Open weight
0.6%
82
Gemma 3 27BGoogle · Open weight
0.1%

The published AA Agentic Index snapshot places Claude Fable 5.1 first at 58.0%. The third row is 2.3 points behind. The broader top-10 range is 8.4 points, so many of the published results sit in a relatively narrow band.

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

About AA Agentic Index

Year

2026

Tasks

Cross-benchmark agentic index

Format

Aggregated model score

Difficulty

Display-only external reference

BenchLM mirrors this agentic index for comparison, but does not use it as a weighted agentic benchmark row.

Artificial Analysis model leaderboards

BenchLM freshness & provenance

Version

AA Agentic Index 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 Agentic Index measure?

A display-only Artificial Analysis agentic index.

Which model scores highest on AA Agentic Index?

Claude Fable 5.1 by Anthropic currently leads with a score of 58.0% on AA Agentic Index.

How many models are evaluated on AA Agentic Index?

82 AI models have been evaluated on AA Agentic Index on BenchLM.

Compare Top Models on AA Agentic Index

Claude Fable 5.1 vs Claude Opus 5Claude Opus 5 vs Muse Spark 1.3Muse Spark 1.3 vs GLM-5.3GLM-5.3 vs Grok 4.6
Last updated: September 10, 2026 · BenchLM version AA Agentic Index 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.