DruxAI
DruxAI

Live Leaderboard

AI Model Rankings

Global benchmarks from Artificial Analysis — plus real-world performance data from every query run on Drux.

Rankings last updated: 20261006 · 100 models

#ModelIntelligence
1Claude Opus 5.5 (Max, Default Fallback)
57.6
2Claude Sonnet 5.5 (Max, Default Fallback)
56
3Claude Opus 5.5 (Xhigh, Default Fallback)
56
4Claude Opus 5.5 (High, Default Fallback)
53.6
5Claude Fable 5.1 (Max, Default Fallback)
53.4
6Claude Fable 5.1 (Xhigh, Default Fallback)
53.2
7GPT-6 Astra (Max)
52.7
8Gemini 4 Argon (High)
52.6
9GPT-6 Astra (Xhigh)
52.4
10Claude Sonnet 5.5 (Xhigh, Default Fallback)
51.9
11GPT-6.1 Sol (Max)
51.8
12Claude Opus 5.5 (Medium, Default Fallback)
51.2
13Claude Fable 5.1 (High, Default Fallback)
51.2
14GPT-6.1 Sol (Xhigh)
51
15GPT-6 Astra (High)
50.9
16Claude Opus 5 (Max)
50.8
17GPT-6.1 Sol (High)
50.2
18Claude Opus 5 (Xhigh)
49.7
19Claude Fable 5 (Max, Opus 4.8 Fallback)
49.6
20GPT-6 Astra (Medium)
49.6
21Claude Fable 5.1 (Medium, Default Fallback)
48.9
22Claude Opus 5 (High)
48.1
23Muse Spark 1.3 (Max)
48.1
24GPT-6.1 Sol (Medium)
47.8
25GPT-6 Sol (Max)
47.6
26GPT-5.6 Sol (Max)
47
27Claude Fable 5.1 (Low, Default Fallback)
46.8
28Claude Sonnet 5.5 (High, Default Fallback)
46.8
29Grok 4.7 (Xhigh)
46.4
30Grok 4.7 (High)
46.3
31MiMo-V2.6-Pro
46.3
32GPT-6 Astra (Low)
45.8
33Qwen3.8 Max (0902)
45.4
34Muse Spark 1.3 (Xhigh)
45.1
35Claude Opus 5 (Medium)
44.8
36GLM-5.3 (Max)
44.8
37Grok 4.6 (High)
44.3
38GPT-6 Sol (Xhigh)
44.2
39Grok 4.6 (Xhigh)
44.2
40GPT-5.6 Sol (Xhigh)
44
41Step 5 Preview
43.7
42Kimi K3 (Max)
43.6
43Grok 4.6 (Medium)
42.8
44GPT-6 Sol (High)
42.4
45GPT-5.6 Sol (High)
42.3
46Claude Opus 5.5 (Low, Default Fallback)
42.3
47Grok 4.7 (Low)
42.2
48GPT-6.1 Sol (Low)
42.1
49GPT-5.6 Terra (Max)
42.1
50GLM 5.3 Flash
41.8
51Claude Opus 4.8 (Max)
41.8
52Ling 3.1 Flash
41.1
53Gemini 3.8 Flash (High)
40.9
54Claude Sonnet 5.5 (Medium, Default Fallback)
40.8
55Claude Opus 4.7 (Max)
40.7
56Qwen3.8 Max
40.2
57Qwen3.8 2.4T A95B
39.9
58Qwen3.8-Flash-Next
39.8
59GPT-6 Sol (Medium)
39.8
60Gemini 3.8 Flash (Medium)
39.8
61Gemini 3.7 Flash (Medium)
39.6
62Muse Spark 1.2 (Xhigh)
39.6
63DeepSeek V4.1 Flash (Max)
39.5
64Claude Opus 5 (Low)
39.4
65GPT-5.6 Sol (Medium)
39.2
66Gemini 3.7 Flash (High)
39.1
67GPT-5.4 (Xhigh)
39
68Grok 4.5 (High)
38.8
69GPT-5.5 (Xhigh)
38.4
70Claude Sonnet 5 (Max)
38.2
71GPT-6 Luna (Max)
38.1
72GPT-5.6 Terra (Xhigh)
38
73MiMo-V2.6-Flash
37.9
74GPT-5.6 Luna (Max)
37.3
75GPT-5.5 (High)
37
76Gemini 3.7 Flash (Low)
36.9
77DeepSeek V4 Pro 0813 (Max)
36
78Claude Sonnet 5.5 (Low, Default Fallback)
35.9
79Grok 4.6 (Low)
35.1
80DeepSeek V4 Flash Vision (Max)
34.8
81GPT-6 Luna (Xhigh)
34.6
82GPT-5.6 Luna (Xhigh)
34.6
83Claude Sonnet 5 (Xhigh)
34.4
84DeepSeek V4 Flash 0731 (Max)
34.3
85GLM-5.3 (Low)
34.3
86GPT-5.6 Terra (High)
34.2
87GPT-6 Sol (Low)
34.2
88Gemini 3.6 Flash (High)
34
89JT-4.1 Flash 236B A21B (Reasoning)
33.9
90GPT-5.5 (Medium)
33.8
91Muse Spark 1.1 (Xhigh)
33.7
92GLM-5.2 (Max)
33.7
93Qwen3.8 27B (Xhigh)
33.7
94Gemini 3.5 Flash (Medium)
33.6
95Motif 3
33.6
96GPT-5.6 Sol (Low)
33.5
97Gemini 3.8 Flash (Low)
33.5
98GPT-6 Luna (High)
32.9
99Gemini 3.5 Flash (High)
32.6
100GPT-5.3 Codex (Xhigh)
32.5

Get the DruxAI daily digest

AI Rankings movers, fresh Hub stories, and the hottest RoundTable debate — in one email.

About this ranking

Intelligence Index is a composite quality score aggregating performance across reasoning, coding, math, and instruction-following benchmarks into a single comparable number.

Data source: Artificial Analysis — independent AI benchmarking. Intelligence Index, benchmark scores, pricing, and speed data are © Artificial Analysis. DruxAI fetches this data daily via the Artificial Analysis API and does not modify or influence the scores.