Intelligence Index

Ein zusammengesetzter Benchmark, der neun anspruchsvolle Evaluierungen aggregiert, um die KI-Fähigkeiten in Wissensarbeit, Programmierung, Wissenschaft und Allgemeinwissen ganzheitlich zu messen.

Zusammengestellt von: Artificial Analysis
Kategorie: Kombiniert
Modelle: 104 aktuell, 119 insgesamt
Median: 29.9
Bereich: 1.8–64.6

Bewertungsverteilung

Niedrigste: 1.8
Median: 29.9
Höchste: 64.6

Komponenten

Bestenliste

Veraltete Modelle einschließen

Rang	Modell	Ergebnis	Kosten / Aufgabe	Zeit / Aufgabe	Output-Tokens / Aufgabe
1	Claude Fable 5.2 (Max, Default Fallback) Anthropic	64.6	$26.54	44m 24s	274K
2	Claude Fable 5.2 (Xhigh, Default Fallback) Anthropic	62.2	$14.83	26m 9s	162K
3	Claude Fable 5.2 (High, Default Fallback) Anthropic	61.8	$9.08	17m 29s	97.8K
4	Gemini 4 Carbon (High) Google	60.0	$7.76	24m 54s	123K
5	Claude Opus 5.5 (Max, Default Fallback) Anthropic	59.1	$10.04	24m 43s	173K
6	Gemini 4 Carbon (Medium) Google	58.3	$6.59	23m 16s	103K
7	Claude Opus 5.5 (Xhigh, Default Fallback) Anthropic	57.4	$6.05	15m 53s	103K
8	GPT-6 Astra (Max) OpenAI	56.9	$6.24	23m 1s	52K
9	Claude Fable 5.2 (Medium, Default Fallback) Anthropic	56.4	$3.80	7m 55s	43.1K
10	GPT-6 Astra (Xhigh) OpenAI	55.3	$3.66	11m 27s	26.7K
11	GPT-6 Astra (High) OpenAI	54.8	$3.24	9m 48s	23.1K
12	GPT-6.1 Sol (Max) OpenAI	54.6	$1.27	20m 7s	67.8K
13	Claude Sonnet 5.5 (Max, Default Fallback) Anthropic	54.5	$10.02	30m 58s	285K
14	Gemini 4 Carbon (Low) Google	54.2	$7.19	22m 17s	86.2K
15	Claude Fable 5.2 (Low, Default Fallback) Anthropic	53.9	$3.10	6m 26s	35.9K
16	GPT-6.1 Sol (Xhigh) OpenAI	52.5	$0.76	9m 2s	30.2K
17	Claude Opus 5.5 (High, Default Fallback) Anthropic	51.8	$3.46	9m 33s	60.1K
18	GPT-6 Astra (Medium) OpenAI	51.6	$2.73	7m 3s	18.1K
19	GPT-6.1 Terra (Max) OpenAI	51.3	$0.96	13m 36s	59.9K
20	Gemini 4 Argon (High) Google	50.4	$9.95	28m 37s	116K
21	GPT-6.1 Sol (High) OpenAI	50.3	$0.59	6m 37s	22.6K
22	Muse Wonder Full (Max) Meta	50.1	—	—	88.5K
23	Claude Sonnet 5.5 (Xhigh, Default Fallback) Anthropic	49.9	$4.09	14m 39s	122K
24	Claude Opus 5.5 (Medium, Default Fallback) Anthropic	48.2	$2.45	7m 4s	43.8K
25	Kimi K3.1 Pro Kimi	46.5	$3.68	37m 7s	72.2K
26	GPT-6.1 Sol (Medium) OpenAI	46.3	$0.36	3m 49s	13.5K
27	GPT-6.1 Terra (Xhigh) OpenAI	45.3	$0.40	6m 5s	26.2K
28	Muse Wonder (Max) Meta	43.6	$6.95	13m 8s	96.1K
29	GPT-6 Astra (Low) OpenAI	43.3	$1.42	3m 50s	9.13K
30	GPT-6.1 Terra (High) OpenAI	42.4	$0.26	3m 59s	16.7K
31	Claude Sonnet 5.5 (High, Default Fallback) Anthropic	41.5	$1.64	6m 54s	58.4K
32	Muse Wonder (High) Meta	40.5	$4.56	9m 20s	67.9K
33	GPT-6.1 Terra (Medium) OpenAI	38.2	$0.17	2m 37s	10.9K
34	Claude Haiku 5.5 (Max) Anthropic	36.5	$0.41	14m 49s	226K
35	Muse Ember (Max) Meta	36.0	$0.14	3m 6s	84.5K
36	Grok 4.7 (Xhigh) SpaceXAI	35.5	$7.77	27m 15s	105K
37	Grok 4.7 (High) SpaceXAI	35.2	$6.18	22m 4s	89.1K
38	GPT-6.1 Sol (Low) OpenAI	34.8	$0.16	1m 43s	5.84K
39	Claude Opus 5.5 (Low, Default Fallback) Anthropic	34.8	$0.98	2m 56s	19.1K
40	Claude Haiku 5.5 (Xhigh) Anthropic	34.6	$0.25	9m 35s	136K
41	Tencent Hy4 Tencent	34.6	$1.03	—	78.1K
42	Muse Ember (Xhigh) Meta	34.1	$0.12	2m 38s	72.4K
43	Qwen3.8 Max (0902) Alibaba	33.7	$10.02	55m 45s	171K
44	DeepSeek V4.1 Flash 1017 (Max) DeepSeek	32.6	$0.60	16m 46s	139K
45	GLM-5.3 (Max) Z AI	31.7	$5.01	28m 52s	119K
46	Grok 4.7 (Low) SpaceXAI	31.1	$2.92	11m 1s	42.7K
47	Gemini 3.8 Flash (High) Google	30.8	$7.77	14m 21s	98.9K
48	Claude Sonnet 5.5 (Medium, Default Fallback) Anthropic	30.8	$0.78	3m 41s	30.7K
49	Inkling 2 Small Thinking Machines	30.6	$1.18	19m 34s	150K
50	GPT-6.1 Terra (Non-reasoning) OpenAI	30.5	$0.23	2m 17s	9.49K

1
Claude Fable 5.2 (Max, Default Fallback)
Anthropic
64.6
$26.54
44m 24s
274K
2

Daten von Artificial Analysis

Command Palette

Intelligence Index

Bewertungsverteilung

Komponenten

Bestenliste