llm.ing

AA Agentic Index

run by Artificial Analysisunit: indexDisplay with attribution; no redistribution85 modelssource ↗
AA Intelligence IndexAA Coding IndexAA Agentic IndexMedian output speedMedian time to first token
#ModelScoreObserved
1Claude Fable 5.1
57.9
independent
Sep 20, 2026
2Claude Opus 5
56.5
mirror
Sep 20, 2026
3Qwen3.8 Max
56.0
mirror
Sep 20, 2026
4Muse Spark 1.3
55.5
mirror
Oct 5, 2026
5Qwen3.8 Flash
53.6
mirror
Nov 18, 2026
6GLM-5.3
53.1
mirror
Sep 20, 2026
7Grok 4.6
52.5
mirror
Nov 5, 2026
8GPT-6 Astra
51.0
independent
Sep 20, 2026
9GLM-5.3-Flash
50.9
independent
Sep 20, 2026
10Claude Fable 5
50.7
mirror
Sep 20, 2026
11DeepSeek V4 Flash Vision Exp
47.5
mirror
Oct 5, 2026
12GPT-5.6 Sol
47.4
mirror
Oct 28, 2026
13Qwen3.8 27B
45.8
mirror
Nov 15, 2026
14GPT-5.4
44.2
mirror
Aug 7, 2026
15Claude Sonnet 5
43.6
independent
Sep 20, 2026
16GPT-5.6 Terra
43.2
mirror
Sep 20, 2026
16Muse Spark 1.2
43.2
independent
Sep 20, 2026
18GPT-5.6 Luna
42.1
independent
Sep 20, 2026
19Claude Opus 4.8
41.9
mirror
Sep 20, 2026
20DeepSeek V4 Pro
41.3
mirror
Sep 20, 2026
21Grok 4.5
41.2
mirror
Sep 20, 2026
22DeepSeek V4 Flash
41.0
mirror
Sep 20, 2026
23Gemini 3.8 Flash
40.2
mirror
Sep 20, 2026
24Claude Opus 4.7
38.6
mirror
Sep 20, 2026
25GLM-5.2
38.4
mirror
Sep 20, 2026
26GPT-5.5
36.4
independent
Sep 20, 2026
27Gemini 3.7 Flash
35.2
mirror
Sep 20, 2026
28Claude Sonnet 4.6
31.8
mirror
Sep 20, 2026
29MiniMax-M3
29.5
independent
Sep 20, 2026
30Kimi K3
29.3
mirror
Oct 30, 2026
31Gemini 3.6 Flash
29.0
mirror
Sep 20, 2026
31Qwen3.6 Plus
29.0
mirror
Aug 7, 2026
33Grok Build 0.1
28.9
independent
Aug 7, 2026
34GPT-5
26.5
independent
Aug 7, 2026
35GLM-4.7
26.2
mirror
Aug 7, 2026
36Gemini 3.5 Flash
26.0
independent
Sep 20, 2026
37MiniMax-M2.7
25.9
independent
Aug 7, 2026
38Muse Spark 1.1
25.8
mirror
Sep 20, 2026
39GLM-5.1
23.9
mirror
Sep 20, 2026
40Qwen3.6 27Bnon-reasoning
23.6
independent
Aug 7, 2026
41Qwen3.7 Max
22.5
mirror
Sep 20, 2026
42Kimi K2.5
21.7
mirror
Jul 23, 2026
42Step 3.7 Flash
21.7
mirror
Aug 7, 2026
44GPT-5.1
21.6
independent
Aug 7, 2026
45Kimi K2.7 Code
21.0
mirror
Sep 20, 2026
46Kimi K2.6
20.5
mirror
Sep 20, 2026
47Nemotron 3 Ultra 550B A55B
20.1
mirror
Sep 20, 2026
48GLM-4.6
18.6
mirror
Aug 7, 2026
49DeepSeek V3.2
18.3
mirror
Jul 23, 2026
50GPT-5.4 mini
17.9
mirror
Sep 20, 2026
51Qwen3.7 Plus
17.5
mirror
Sep 20, 2026
52Qwen3.5 122B-A10Bnon-reasoning
16.2
independent
Aug 7, 2026
53GPT-5.4 nano
16.0
mirror
Sep 20, 2026
54Claude Sonnet 4.5 (latest)
15.8
mirror
Sep 20, 2026
55Grok 4.3
15.5
mirror
Sep 20, 2026
56Gemini 3.5 Flash Lite
14.3
independent
Sep 20, 2026
57Qwen3.6 35B-A3B
13.1
mirror
Sep 20, 2026
58Qwen3.5 35B-A3B
11.8
mirror
Jul 23, 2026
59Qwen3.5 397B-A17B
8.3
independent
Sep 20, 2026
60Gemini 3.1 Pro Preview
8.2
mirror
Sep 20, 2026
61Claude Haiku 4.5 (latest)
8.0
mirror
Sep 20, 2026
62GPT-5 Mini
6.8
independent
Sep 20, 2026
63Gemma 4 31B IT
4.2
mirror
Sep 20, 2026
64Gemma 4 26B A4B IT
2.9
mirror
Oct 5, 2026
65Devstral 2
2.3
mirror
Sep 20, 2026
66Qwen3-Next 80B-A3B (Thinking)thinking
2.1
mirror
Jul 23, 2026
67GPT-4.1 mini
1.8
mirror
Aug 7, 2026
67Kimi K2 Thinkingthinking
1.8
mirror
Jul 23, 2026
69Nemotron 3 Super
1.7
mirror
Sep 20, 2026
70Gemini 3.1 Flash Lite Preview
1.6
mirror
Sep 20, 2026
70Gemini 2.5 Pro
1.6
independent
Sep 20, 2026
70Mercury 2
1.6
independent
Sep 20, 2026
73Qwen3 235B-A22Bthinking
1.3
mirror
Sep 8, 2026
74GPT-4.1 nano
1.2
mirror
Jul 23, 2026
75DeepSeek R1
1.1
independent
Sep 7, 2026
75Ministral 3 14B
1.1
mirror
Oct 7, 2026
77GPT-4o mini
1.0
mirror
Jul 23, 2026
77nemotron-3-nano-30b-a3b
1.0
mirror
Sep 8, 2026
79o3-minihigh-effort
0.9
independent
Sep 7, 2026
79Qwen3 32B
0.9
mirror
Sep 8, 2026
79Qwen3 14B
0.9
mirror
Sep 8, 2026
82Qwen3 8B
0.8
mirror
Sep 8, 2026
82Ministral 3 3B
0.8
mirror
Oct 7, 2026
84Ministral 3 8B
0.6
mirror
Oct 7, 2026
85Llama-3.3-70B-Instruct
0.3
mirror
Jul 23, 2026

Bars on a 0–60 index scale. Scores link to model pages; every number keeps its source on the model page.