LLM-Benchmarks

Name: Wikiprompt LLM Benchmarks
Creator: Wikiprompt
License: https://creativecommons.org/licenses/by-sa/4.0/

Von Wikiprompt, der freien Prompt-Enzyklopadie

Live-Ranglisten fur Sprachmodelle und generative KI, taglich aus offenen Community-Bewertungen aggregiert. Jede Tabelle nennt ihre Quelle, und da Wikiprompt taglich einen Snapshot speichert, bleiben Verschiebungen in den Rankings dokumentiert.

Zuletzt aktualisiert: 2026-08-24 · Dies ist die LIVE-Rangliste; datierte Snapshots bewahren jede fruhere Platzierung. Verlauf →

Interaktiver Explorer

Nach Arena, Organisation oder Lizenz filtern, Modelle suchen, Tabelle sortieren und das Kosten-Leistungs-Diagramm lesen. Die Tabellen darunter bleiben die zitierbare Referenz.

Text-Arena

Zeilen oder Diagrammpunkte anklicken, um Modelle zu fixieren und nur diese zu vergleichen.

Kosten vs. Leistung

Ausgabepreis in USD pro 1M Tokens (Log-Skala, OpenRouter) vs. Community-Elo (LMArena). Oben links = bestes Preis-Leistungs-Verhaltnis.

Elo im Zeitverlauf (Top-Textmodelle)

Rang ▲	Modell	Organisation	Elo-Wert	Stimmen	Eingabe $/1M	Ausgabe $/1M	Kontext
1	claude-opus-5-high	anthropic	1,504	27,610	$10	$50	1,000,000
3	claude-opus-4-6-high	anthropic	1,503	72,359	$5	$25	1,000,000
4	claude-opus-4-6	anthropic	1,497	76,362	$5	$25	1,000,000
5	claude-fable-5	anthropic	1,495	24,331	$10	$50	1,000,000
7	claude-opus-4-7-high	anthropic	1,490	60,203	$5	$25	1,000,000
9	claude-opus-4-7	anthropic	1,483	61,304	$5	$25	1,000,000
10	gemini-3.5-flash-high	google	1,483	30,004	$1.5	$9	1,048,576
12	gemini-3.1-pro-preview	google	1,480	99,182	$2	$12	1,048,576
13	gemini-3-pro	google	1,479	41,491	$2	$12	131,072
14	muse-spark-1.1	meta	1,478	20,242	$1.25	$4.25	1,048,576
18	gemini-3.5-flash-medium	google	1,475	28,343	$1.5	$9	1,048,576
21	qwen3.5-max-preview	alibaba	1,471	21,484
22	gpt-5.5-high	openai	1,471	59,545	$5	$30	1,050,000
23	gpt-5.4-high	openai	1,470	60,708	$2.5	$15	1,050,000
24	ernie-5.1	baidu	1,468	37,137
25	gemini-3-flash	google	1,466	30,852	$0.5	$3	1,048,576
26	gpt-5.5	openai	1,466	60,896	$5	$30	1,050,000
27	glm-5.2-max	zai	1,465	30,637	$0.97	$3.04	1,048,576
28	mimo-v2.5-pro	xiaomi	1,465	54,177	$0.44	$0.87	1,050,000
29	glm-5.1	zai	1,464	42,267	$0.97	$3.04	204,800
30	claude-opus-4-8-high	anthropic	1,461	44,676	$5	$25	1,000,000
31	claude-sonnet-4-6	anthropic	1,458	66,512	$2	$10	1,000,000
32	gemini-2.5-pro	google	1,457	124,807	$1.25	$10	1,048,576
33	qwen3.7-plus	alibaba	1,456	34,426	$0.32	$1.28	1,000,000
34	kimi-k2.6	moonshot	1,455	37,543	$0.95	$4	262,144
35	gpt-5.6-sol-xhigh	openai	1,454	19,541	$2	$10	1,050,000
36	gpt-5.4	openai	1,453	63,659	$2.5	$15	1,050,000
37	grok-4.5	xai	1,452	22,030	$2	$6	500,000
38	claude-opus-4-8	anthropic	1,452	45,331	$5	$25	1,000,000
39	grok-4.20-beta-0309-reasoning	xai	1,451	62,272	$1.25	$2.5	2,000,000
40	deepseek-v4-pro	deepseek	1,451	54,263	$0.52	$1.04	1,048,576
41	grok-4.20-multi-agent-beta-0309	xai	1,450	60,864	$1.25	$2.5	2,000,000
42	claude-opus-4-5-20251101	anthropic	1,450	70,985	$5	$25	1,000,000
43	dola-seed-2.0-pro	bytedance	1,448	74,513
45	claude-opus-4-5-20251101-high-32k	anthropic	1,447	37,198	$5	$25	1,000,000
47	gpt-5.6-terra-xhigh	openai	1,446	20,216	$2	$12	1,050,000
48	glm-5	zai	1,445	27,850	$0.6	$1.92	204,800
49	kimi-k2.5-thinking	moonshot	1,445	70,943	$0.45	$2.25	262,144
50	deepseek-v4-pro-high-preview	deepseek	1,445	51,642	$0.52	$1.04	1,048,576
52	ernie-5.0-0110	baidu	1,444	35,267
53	grok-4.20-beta1	xai	1,444	26,770	$1.25	$2.5	2,000,000
56	gemini-3-flash (thinking-minimal)	google	1,442	86,359	$0.5	$3	1,048,576
57	claude-sonnet-5-high	anthropic	1,442	27,366	$2	$10	1,000,000
59	gpt-5.1-high	openai	1,441	40,945	$1.25	$10	400,000
62	glm-4.6	zai	1,440	35,830	$0.5	$2	204,800
65	qwen3-max-preview	alibaba	1,439	27,838	$0.78	$3.9	262,144
66	gpt-5.2-chat-latest-20260210	openai	1,439	34,339	$1.75	$14	128,000
67	qwen3.5-397b-a17b	alibaba	1,438	70,207	$0.5	$3.6	262,144
68	claude-sonnet-4-5-20250929	anthropic	1,438	80,858	$2	$10	1,000,000
69	grok-4.1-thinking	xai	1,437	65,550
70	qwen3.6-plus	alibaba	1,437	45,376	$0.33	$1.95	1,000,000
72	mimo-v2-pro	xiaomi	1,437	24,397
74	grok-4.1	xai	1,436	67,767
76	minimax-m3	minimax	1,435	41,023	$0.3	$1.2	1,048,576
78	claude-sonnet-4-5-20250929-high-32k	anthropic	1,433	82,473	$2	$10	1,000,000
79	deepseek-v4-flash	deepseek	1,432	49,001	$0.04	$0.08	1,310,720
80	glm-4.5	zai	1,429	24,403	$0.6	$2.2	131,072
82	chatgpt-4o-latest-20250326	openai	1,429	82,766
83	gpt-5.6-luna-xhigh	openai	1,429	20,693	$0.2	$1.2	1,050,000
84	mistral-large-3	mistral	1,428	62,644	$0.5	$1.5	262,144

Preise werden per normalisiertem Modellnamen dem nachsten OpenRouter-Listing zugeordnet; Reasoning-Varianten teilen den Basispreis.

Fazit

• Aktueller Text-Arena-Fuhrer: claude-opus-5-high (anthropic, Elo 1504)
• Bestes Preis-Leistungs-Verhaltnis (Elo pro Dollar, unter $2/1M Output): mimo-v2.5-pro (Elo 1465, $0.87/1M)
• Starkstes offenes Modell: glm-5.2-max (MIT, #27)
• Coding-Fuhrer (Aider Pass Rate): gpt-5 (high) (88%)

Inhalt

Text-Arena
Webentwicklungs-Arena
Vision-Arena
Text-zu-Bild-Arena
Bildbearbeitungs-Arena
Text-zu-Video-Arena
Videobearbeitungs-Arena
Such-Arena
Agenten-Arena
Dokumenten-Arena
Preise und Kontextfenster
Letzte Anderungen
Quellen und Methodik

Text-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	claude-opus-5-high	anthropic	1,504	1,499 / 1,509	27,610	Proprietary
3	claude-opus-4-6-high	anthropic	1,503	1,499 / 1,506	72,359	Proprietary
4	claude-opus-4-6	anthropic	1,497	1,494 / 1,501	76,362	Proprietary
5	claude-fable-5	anthropic	1,495	1,490 / 1,500	24,331	Proprietary
7	claude-opus-4-7-high	anthropic	1,490	1,486 / 1,494	60,203	Proprietary
9	claude-opus-4-7	anthropic	1,483	1,479 / 1,487	61,304	Proprietary
10	gemini-3.5-flash-high	google	1,483	1,478 / 1,487	30,004	Proprietary
12	gemini-3.1-pro-preview	google	1,480	1,476 / 1,483	99,182	Proprietary
13	gemini-3-pro	google	1,479	1,476 / 1,483	41,491	Proprietary
14	muse-spark-1.1	meta	1,478	1,473 / 1,484	20,242	Proprietary
18	gemini-3.5-flash-medium	google	1,475	1,470 / 1,480	28,343	Proprietary
21	qwen3.5-max-preview	alibaba	1,471	1,466 / 1,476	21,484	Proprietary
22	gpt-5.5-high	openai	1,471	1,467 / 1,475	59,545	Proprietary
23	gpt-5.4-high	openai	1,470	1,466 / 1,473	60,708	Proprietary
24	ernie-5.1	baidu	1,468	1,463 / 1,473	37,137	Proprietary
25	gemini-3-flash	google	1,466	1,462 / 1,470	30,852	Proprietary
26	gpt-5.5	openai	1,466	1,462 / 1,470	60,896	Proprietary
27	glm-5.2-max	zai	1,465	1,461 / 1,470	30,637	MIT
28	mimo-v2.5-pro	xiaomi	1,465	1,461 / 1,469	54,177	MIT
29	glm-5.1	zai	1,464	1,460 / 1,468	42,267	MIT
30	claude-opus-4-8-high	anthropic	1,461	1,457 / 1,465	44,676	Proprietary
31	claude-sonnet-4-6	anthropic	1,458	1,454 / 1,461	66,512	Proprietary
32	gemini-2.5-pro	google	1,457	1,455 / 1,460	124,807	Proprietary
33	qwen3.7-plus	alibaba	1,456	1,452 / 1,461	34,426	Proprietary
34	kimi-k2.6	moonshot	1,455	1,450 / 1,460	37,543	Modified MIT

Webentwicklungs-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	claude-opus-5-max	anthropic	1,691	1,682 / 1,699	8,116	Proprietary
2	kimi-k3-max	moonshot	1,674	1,662 / 1,685	4,546	Kimi K3 license
3	qwen3.8-max	alibaba	1,669	1,656 / 1,681	3,212	Proprietary
4	claude-opus-5-high	anthropic	1,663	1,655 / 1,671	8,659	Proprietary
5	grok-4.6-high	xai	1,629	1,612 / 1,646	1,523	Proprietary
6	claude-fable-5	anthropic	1,626	1,618 / 1,634	8,382	Proprietary
7	gpt-5.6-sol-xhigh (codex-harness)	openai	1,619	1,611 / 1,626	9,499	Proprietary
8	glm-5.3-max	zai	1,599	1,583 / 1,614	1,916	MIT
9	qwen3.8-27b	alibaba	1,595	1,582 / 1,608	2,464	Apache 2.0
10	gemini-3.7-flash-high	google	1,587	1,574 / 1,600	2,552	Proprietary
11	glm-5.2-max	zai	1,582	1,574 / 1,590	8,775	MIT
12	deepseek-v4-pro-high-20260813	deepseek	1,582	1,570 / 1,594	2,869	MIT
13	deepseek-v4-flash-high	deepseek	1,579	1,568 / 1,590	3,537	MIT
14	claude-opus-4-8-high	anthropic	1,563	1,556 / 1,571	11,699	Proprietary
15	claude-opus-4-7	anthropic	1,558	1,551 / 1,564	14,527	Proprietary
16	claude-opus-4-7-high	anthropic	1,557	1,550 / 1,563	15,099	Proprietary
17	grok-4.5	xai	1,556	1,548 / 1,565	6,325	Proprietary
18	claude-opus-4-6-high	anthropic	1,546	1,540 / 1,551	17,015	Proprietary
19	claude-opus-4-8	anthropic	1,539	1,532 / 1,546	10,638	Proprietary
20	muse-spark-1.1	meta	1,539	1,531 / 1,548	6,204	Proprietary
21	gemini-3.6-flash-high	google	1,539	1,530 / 1,547	6,464	Proprietary
22	claude-sonnet-5-high	anthropic	1,539	1,531 / 1,547	7,267	Proprietary
23	claude-opus-4-6	anthropic	1,536	1,531 / 1,542	18,226	Proprietary
24	muse-spark-1.2 (xHigh)	meta	1,534	1,520 / 1,548	2,062	Proprietary
25	claude-sonnet-4-6	anthropic	1,522	1,517 / 1,528	20,307	Proprietary

Vision-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	claude-fable-5	anthropic	1,328	1,319 / 1,337	9,562	Proprietary
2	claude-opus-5-high	anthropic	1,323	1,314 / 1,331	7,049	Proprietary
3	claude-opus-4-7	anthropic	1,317	1,310 / 1,323	21,445	Proprietary
4	claude-opus-4-7-high	anthropic	1,316	1,309 / 1,322	21,122	Proprietary
5	qwen3.8-max	alibaba	1,315	1,306 / 1,323	6,743	Proprietary
6	claude-opus-4-6-high	anthropic	1,315	1,308 / 1,321	20,867	Proprietary
7	gemini-3.5-flash-high	google	1,313	1,304 / 1,321	7,586	Proprietary
8	claude-opus-4-6	anthropic	1,311	1,305 / 1,318	25,169	Proprietary
9	gemini-3.5-flash-medium	google	1,308	1,300 / 1,317	7,533	Proprietary
10	muse-spark	meta	1,306	1,297 / 1,316	5,582	Proprietary
11	gemini-3-pro	google	1,305	1,298 / 1,313	13,134	Proprietary
12	muse-spark-1.2 (xHigh)	meta	1,304	1,290 / 1,319	1,853	Proprietary
13	gemini-3.6-flash-high	google	1,302	1,290 / 1,314	3,119	Proprietary
14	gpt-5.4-high	openai	1,297	1,290 / 1,304	22,515	Proprietary
15	gpt-5.5	openai	1,295	1,289 / 1,302	20,727	Proprietary
16	muse-spark-1.1	meta	1,295	1,286 / 1,303	6,142	Proprietary
17	gemini-3.1-pro-preview	google	1,294	1,288 / 1,300	38,674	Proprietary
18	claude-opus-4-8-high	anthropic	1,293	1,286 / 1,301	12,894	Proprietary
19	gpt-5.5-high	openai	1,293	1,286 / 1,300	19,406	Proprietary
20	gpt-5.4	openai	1,293	1,286 / 1,300	21,227	Proprietary
21	grok-4.5	xai	1,291	1,282 / 1,301	5,722	Proprietary
22	claude-opus-4-8	anthropic	1,287	1,280 / 1,295	13,354	Proprietary
23	gemini-3-flash	google	1,283	1,278 / 1,288	36,437	Proprietary
24	claude-sonnet-4-6	anthropic	1,281	1,275 / 1,288	25,559	Proprietary
25	claude-sonnet-5-high	anthropic	1,281	1,273 / 1,290	7,862	Proprietary

Text-zu-Bild-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	gpt-image-2 (medium)	openai	1,380	1,376 / 1,385	69,194	Proprietary
2	reve-2.1	reve	1,302	1,294 / 1,309	7,598	Proprietary
3	muse-image	meta	1,283	1,277 / 1,290	14,510	Proprietary
4	reve-2.0	reve	1,270	1,264 / 1,276	14,650	Proprietary
5	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,263	1,258 / 1,268	27,910	Proprietary
6	qwen-image-3.0-pro	alibaba	1,258	1,248 / 1,267	3,735	Proprietary
7	seedream-5.0-pro	bytedance	1,257	1,252 / 1,262	26,510	Proprietary
8	mai-image-2.5	microsoft-ai	1,256	1,252 / 1,261	44,940	Proprietary
9	gemini-3.1-flash-lite-image (nano-banana-2-lite)	google	1,251	1,245 / 1,257	16,419	Proprietary
10	gemini-3-pro-image-2k (nano-banana-pro)	google	1,246	1,242 / 1,249	138,756	Proprietary
11	gpt-image-1.5-high-fidelity	openai	1,239	1,235 / 1,242	142,427	Proprietary
12	gemini-3-pro-image-preview (nano-banana-pro)	google	1,232	1,227 / 1,237	82,835	Proprietary
13	grok-imagine-image-quality	xai	1,228	1,224 / 1,232	48,786	Proprietary
14	ideogram-4.0-quality	ideogram	1,206	1,201 / 1,210	27,891	Ideogram Open Model
15	qwen-image-2.0-pro-2026-06-22	alibaba	1,191	1,185 / 1,197	12,026	Proprietary
16	uni-1.1-max	luma-ai	1,188	1,182 / 1,194	13,491	Proprietary
17	mai-image-2	microsoft-ai	1,182	1,178 / 1,187	49,207	Proprietary
18	Cosmos3-Super-Text2Image (Agentic)	nvidia	1,181	1,170 / 1,191	2,957	OpenMDW-1.1
19	uni-1.1	luma-ai	1,180	1,175 / 1,185	26,927	Proprietary
20	grok-imagine-image	xai	1,172	1,169 / 1,175	217,461	Proprietary
21	recraft-v4.1-utility-pro	recraft	1,169	1,158 / 1,180	2,519	Proprietary
22	flux-2-max	bfl	1,162	1,158 / 1,165	117,464	Proprietary
23	grok-imagine-image-pro	xai	1,161	1,157 / 1,165	93,711	Proprietary
24	Cosmos3-Super-Text2Image	nvidia	1,158	1,150 / 1,167	4,669	OpenMDW-1.1
25	flux-2-flex	bfl	1,156	1,153 / 1,160	149,402	Proprietary

Bildbearbeitungs-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	gpt-image-2 (medium)	openai	1,463	1,459 / 1,466	199,275	Proprietary
2	grok-imagine-image-2.0 (low)	xai	1,439	1,431 / 1,448	5,937	Proprietary
3	mai-image-2.6-preview	microsoft-ai	1,420	1,412 / 1,428	5,563	Proprietary
4	muse-image	meta	1,406	1,401 / 1,412	54,730	Proprietary
5	mai-image-2.5	microsoft-ai	1,401	1,398 / 1,405	170,301	Proprietary
6	seedream-5.0-pro	bytedance	1,394	1,390 / 1,398	102,314	Proprietary
7	grok-imagine-image-quality (20260519)	xai	1,390	1,384 / 1,396	35,601	Proprietary
8	gemini-3-pro-image-2k (nano-banana-pro)	google	1,390	1,387 / 1,392	517,418	Proprietary
9	chatgpt-image-latest-high-fidelity (20251216)	openai	1,389	1,386 / 1,392	508,742	Proprietary
10	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,386	1,383 / 1,390	117,943	Proprietary
11	gemini-3-pro-image-preview (nano-banana-pro)	google	1,385	1,382 / 1,388	519,140	Proprietary
12	reve-2.1	reve	1,375	1,369 / 1,381	19,116	Proprietary
13	gpt-image-1.5-high-fidelity	openai	1,370	1,367 / 1,373	531,138	Proprietary
14	reve-2.0	reve	1,358	1,352 / 1,365	17,508	Proprietary
15	uni-1.1-max	luma-ai	1,334	1,329 / 1,339	40,926	Proprietary
16	grok-imagine-image	xai	1,330	1,327 / 1,333	564,747	Proprietary
17	gemini-3.1-flash-lite-image (nano-banana-2-lite)	google	1,314	1,309 / 1,319	59,307	Proprietary
18	uni-1.1	luma-ai	1,312	1,308 / 1,316	115,289	Proprietary
19	qwen-image-2.0-pro-2026-06-22	alibaba	1,304	1,299 / 1,308	50,798	Proprietary
20	hunyuan-image-3.0-instruct	tencent	1,303	1,299 / 1,306	307,816	tencent-hunyuan-community
21	wan2.7-image-pro	alibaba	1,302	1,298 / 1,306	41,549	Proprietary
22	seedream-4.5	bytedance	1,302	1,300 / 1,304	1,016,857	Proprietary
23	wan2.7-image	alibaba	1,301	1,297 / 1,305	42,386	Proprietary
24	gemini-2.5-flash-image-preview (nano-banana)	google	1,293	1,291 / 1,296	11,129,141	Proprietary
25	seedream-5.0-lite	bytedance	1,293	1,290 / 1,296	332,279	Proprietary

Text-zu-Video-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	gemini-omni-flash	google	1,512	1,501 / 1,522	16,916	Proprietary
2	flux-3-video	bfl	1,494	1,477 / 1,512	1,291	Proprietary
3	dreamina-seedance-2.0-720p	bytedance	1,482	1,472 / 1,491	49,058	Proprietary
4	dreamina-seedance-2.5-720p	bytedance	1,477	1,458 / 1,496	1,337	Proprietary
5	muse-video	meta	1,457	1,442 / 1,472	2,176	Proprietary
6	minimax-h3	minimax	1,453	1,440 / 1,466	3,081	minimax-h3-community-license-agreement
7	happyhorse-1.0	aorizon	1,428	1,415 / 1,441	22,113	Proprietary
8	sora-2-pro	openai	1,364	1,357 / 1,371	46,509	Proprietary
9	veo-3.1-audio	google	1,364	1,350 / 1,378	13,743	Proprietary
10	veo-3.1-audio-1080p	google	1,363	1,353 / 1,373	24,979	Proprietary
11	veo-3.1-fast-audio	google	1,361	1,351 / 1,372	39,441	Proprietary
12	veo-3.1-fast-audio-1080p	google	1,358	1,348 / 1,368	25,771	Proprietary
13	veo-3-fast-audio	google	1,347	1,336 / 1,358	25,219	Proprietary
14	grok-imagine-video-720p	xai	1,345	1,338 / 1,353	154,827	Proprietary
15	wan2.7-t2v	wan	1,344	1,336 / 1,353	17,769	Proprietary
16	sora-2	openai	1,340	1,334 / 1,347	62,692	Proprietary
17	veo-3-audio	google	1,339	1,327 / 1,352	19,007	Proprietary
18	wan2.6-t2v	alibaba	1,330	1,322 / 1,338	44,304	Proprietary
19	seedance-v1.5-pro	bytedance	1,256	1,249 / 1,262	75,990	Proprietary
20	veo-3	google	1,253	1,242 / 1,264	14,986	Proprietary
21	wan2.5-t2v-preview	alibaba	1,249	1,239 / 1,258	28,239	Proprietary
22	veo-3-fast	google	1,248	1,236 / 1,260	15,271	Proprietary
23	pixverse-v5.6		1,240	1,229 / 1,250	32,301	Proprietary
24	runway-gen-4.5	runway	1,223	1,213 / 1,232	38,795	Proprietary
25	kling-2.5-turbo-1080p	kling	1,219	1,201 / 1,236	2,105	Proprietary

Videobearbeitungs-Arena9 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	dreamina-seedance-2.5-720p	bytedance	1,411	1,384 / 1,437	403	Proprietary
2	minimax-h3	minimax	1,388	1,364 / 1,412	554	minimax-h3-community-license-agreement
3	dreamina-seedance-2.0-720p	bytedance	1,359	1,346 / 1,373	3,634	Proprietary
4	gemini-omni-flash	google	1,358	1,343 / 1,372	1,868	Proprietary
5	happyhorse-1.0	aorizon	1,307	1,294 / 1,320	3,115	Proprietary
6	grok-imagine-video	xai	1,262	1,253 / 1,272	13,281	Proprietary
7	kling-o3-pro	kling	1,257	1,245 / 1,268	7,125	Proprietary
8	kling-o1-pro	kling	1,200	1,190 / 1,210	10,104	Proprietary
9	runway-gen4-aleph	runway	1,183	1,175 / 1,191	9,817	Proprietary

Such-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	claude-opus-4-6-search	anthropic	1,253	1,248 / 1,258	112,201	Proprietary
2	gpt-5.5-search	openai	1,240	1,235 / 1,245	67,573	Proprietary
3	claude-fable-5	anthropic	1,237	1,229 / 1,245	20,630	Proprietary
4	claude-opus-4-7	anthropic	1,233	1,227 / 1,238	68,515	Proprietary
5	ernie-5.1	baidu	1,226	1,217 / 1,236	3,815	Proprietary
6	claude-sonnet-4-6-search	anthropic	1,221	1,216 / 1,226	111,959	Proprietary
7	gemini-3.1-pro-grounding	google	1,212	1,207 / 1,218	89,973	Proprietary
8	gemini-3-pro-grounding	google	1,207	1,202 / 1,212	37,255	Proprietary
9	gpt-5.2-search	openai	1,206	1,200 / 1,211	52,718	Proprietary
10	grok-4.20-multi-agent-beta-0309	xai	1,205	1,200 / 1,211	87,118	Proprietary
11	claude-opus-4-8	anthropic	1,205	1,199 / 1,211	48,610	Proprietary
12	gpt-5.1-search	openai	1,199	1,194 / 1,205	60,019	Proprietary
13	gemini-3-flash-grounding	google	1,197	1,193 / 1,202	125,928	Proprietary
14	gpt-5.4-search	openai	1,196	1,190 / 1,201	87,364	Proprietary
15	grok-4.20-beta1	xai	1,189	1,183 / 1,195	53,877	Proprietary
16	claude-sonnet-5-search	anthropic	1,188	1,182 / 1,195	17,604	Proprietary
17	claude-opus-4-5-search	anthropic	1,179	1,173 / 1,185	61,611	Proprietary
18	gpt-5.2-search-non-reasoning	openai	1,173	1,167 / 1,178	75,752	Proprietary
19	grok-4-1-fast-search	xai	1,171	1,166 / 1,176	81,860	Proprietary
20	grok-4-fast-search	xai	1,170	1,166 / 1,175	42,981	Proprietary
21	grok-4.3	xai	1,163	1,158 / 1,168	68,373	Proprietary
22	claude-sonnet-4-5-search	anthropic	1,158	1,154 / 1,163	105,762	Proprietary
23	claude-opus-4-1-search	anthropic	1,148	1,143 / 1,152	77,222	Proprietary
24	o3-search	openai	1,143	1,138 / 1,149	20,785	Proprietary
25	gemini-2.5-pro-grounding	google	1,142	1,138 / 1,147	83,608	Proprietary

Agenten-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Lizenz
1	Claude Opus 5 (High)	anthropic	Proprietary
2	Claude Opus 5 (Max)	anthropic	Proprietary
3	Claude Fable 5 (High)	anthropic	Proprietary
4	Kimi K3 (Max)	moonshot	Kimi K3 license
5	GPT 5.6 Sol (xHigh)	openai	Proprietary
6	Claude Opus 4.8 (High)	anthropic	Proprietary
7	GPT 5.5 (xHigh)	openai	Proprietary
8	Claude Opus 4.7 (High)	anthropic	Proprietary
9	GPT 5.5 (High)	openai	Proprietary
10	Claude Opus 4.7	anthropic	Proprietary
11	Claude Sonnet 5 (High)	anthropic	Proprietary
12	Claude Opus 4.6	anthropic	Proprietary
13	GPT 5.5	openai	Proprietary
14	DeepSeek V4 Pro (High) (0813)	deepseek	MIT
15	Qwen3.8 Max	alibaba	Proprietary
16	Grok 4.5	xai	Proprietary
17	GLM 5.2 (Max)	zai	MIT
18	GPT 5.4 (High)	openai	Proprietary
19	GPT 5.6 Luna (xHigh)	openai	Proprietary
20	Deepseek V4 Flash (High) (20260731)	deepseek	MIT
21	Gemini 3.7 Flash (High)	google	Proprietary
22	GPT 5.6 Terra (xHigh)	openai	Proprietary
23	Claude Sonnet 4.6	anthropic	Proprietary
24	Claude Opus 4.8	anthropic	Proprietary
25	Muse Spark 1.1	meta	Proprietary

Dokumenten-Arena25 ModelleKomplette Rangliste →

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
1	claude-opus-5-high	anthropic	1,520	1,505 / 1,535	1,663	Proprietary
2	claude-opus-4-6	anthropic	1,510	1,504 / 1,516	37,271	Proprietary
3	claude-opus-4-6-thinking	anthropic	1,506	1,499 / 1,513	24,973	Proprietary
4	claude-fable-5	anthropic	1,504	1,495 / 1,513	5,792	Proprietary
5	claude-opus-4-7	anthropic	1,498	1,491 / 1,505	18,990	Proprietary
6	claude-opus-4-7-thinking	anthropic	1,497	1,490 / 1,504	18,793	Proprietary
7	gpt-5.5-high	openai	1,485	1,478 / 1,492	16,816	Proprietary
8	claude-sonnet-4-6	anthropic	1,483	1,476 / 1,489	54,427	Proprietary
9	gpt-5.5	openai	1,480	1,473 / 1,487	17,286	Proprietary
10	gpt-5.6-terra-xhigh	openai	1,479	1,466 / 1,492	1,969	Proprietary
11	gpt-5.6-sol-xhigh	openai	1,479	1,462 / 1,495	1,152	Proprietary
12	claude-opus-4-8-thinking	anthropic	1,475	1,466 / 1,483	8,388	Proprietary
13	muse-spark-1.1	meta	1,472	1,459 / 1,485	2,054	Proprietary
14	claude-sonnet-5-high	anthropic	1,470	1,460 / 1,481	3,601	Proprietary
15	gpt-5.4	openai	1,470	1,464 / 1,477	29,809	Proprietary
16	claude-opus-4-8	anthropic	1,469	1,461 / 1,477	8,193	Proprietary
17	gemini-3.5-flash-medium	google	1,465	1,454 / 1,475	3,689	Proprietary
18	gpt-5.6-luna-xhigh	openai	1,462	1,449 / 1,476	1,888	Proprietary
19	claude-opus-4-5-20251101	anthropic	1,462	1,451 / 1,472	7,965	Proprietary
20	grok-4.5	xai	1,454	1,442 / 1,466	2,435	Proprietary
21	kimi-k2.6	moonshot	1,451	1,443 / 1,459	11,181	Modified MIT
22	claude-sonnet-4-5-20250929	anthropic	1,446	1,440 / 1,453	28,634	Proprietary
23	gemini-3.1-pro-preview	google	1,445	1,439 / 1,451	45,162	Proprietary
24	muse-spark	meta	1,443	1,425 / 1,462	1,078	Proprietary
25	qwen3.7-plus	alibaba	1,440	1,429 / 1,450	3,088	Proprietary

Weitere Ranglisten

LiveBench

Metrik: average score (0-100) · livebench.ai

Rang	Modell	Wert
1	claude-fable-5-max-effort	83.4
2	gpt-5.6-sol-max	81.7
3	gpt-5.5-xhigh	80.8
4	claude-opus-5-max-effort	80.5
5	gemini-3.7-flash-high	79.9
6	smaug-agentic	79.7
7	qwen3.8-max	79.5
8	kimi-k3	79.5
9	grok-4.6	79
10	muse-spark-1.2-xhigh	78.9
11	gpt-5.4-xhigh	78.8
12	gpt-5.6-terra-max	78.6
13	deepseek-v4-pro-0813	78.2
14	gemini-3.1-pro-preview-high	78
15	deepseek-v4-flash-vision-exp	77.7

BenchLM

Metrik: aggregated display score · benchlm.ai

Rang	Modell	Organisation	Wert
1	Claude Mythos 5	Anthropic	83
2	Claude Opus 5	Anthropic	82.7
3	Claude Fable 5	Anthropic	82.7
4	GPT-5.6 Sol	OpenAI	81.7
5	Kimi K3	Moonshot AI	80.2
6	Qwen3.8 Max	Alibaba	79
7	Muse Spark 1.1	Meta	76.7
8	Claude Opus 4.8	Anthropic	76.2
9	Gemini 3.6 Flash	Google	75.2
10	Grok 4.5	xAI	75.2
11	GPT-5.5	OpenAI	73.3
12	GPT-5.4	OpenAI	73.1
13	GPT-5.6 Terra	OpenAI	72.6
14	Claude Opus 4.7 (Adaptive)	Anthropic	72.3
15	Claude Opus 4.7	Anthropic	71.9

Aider polyglot (coding)

Metrik: pass rate 2 (%) · aider.chat/docs/leaderboards/

Rang	Modell	Wert
1	gpt-5 (high)	88
2	gpt-5 (medium)	86.7
3	o3-pro (high)	84.9
4	gemini-2.5-pro-preview-06-05 (32k think)	83.1
5	o3 (high)	81.3
6	gpt-5 (low)	81.3
7	grok-4 (high)	79.6
8	gemini-2.5-pro-preview-06-05 (default think)	79.1
9	o3 (high) + gpt-4.1	78.2
10	Gemini 2.5 Pro Preview 05-06	76.9
11	o3	76.9
12	DeepSeek-V3.2-Exp (Reasoner)	74.2
13	Gemini 2.5 Pro Preview 03-25	72.9
14	o4-mini (high)	72
15	claude-opus-4-20250514 (32k thinking)	72

Artificial Analysis (Intelligence Index)

Metrik: AA Intelligence Index (0-100) · artificialanalysis.ai

Rang	Modell	Organisation	Wert
1	Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	63.1
2	Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	62.5
3	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	62.1
4	Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	61.5
5	GPT-5.6 Sol (max)	OpenAI	60.9
6	Grok 4.6 (high)	SpaceXAI	60.9
7	Grok 4.6 (xhigh)	SpaceXAI	60
8	Kimi K3 (max)	Kimi	59.7
9	GLM-5.3 (max)	Z AI	59.5
10	GPT-5.6 Sol (xhigh)	OpenAI	59
11	Grok 4.6 (medium)	SpaceXAI	59
12	Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	58.6
13	Qwen3.8 Max	Alibaba	58.1
14	Qwen3.8 2.4T A95B	Alibaba	57.7
15	GPT-5.6 Sol (high)	OpenAI	57.3

Preise und Kontextfenster

Preise und Kontext-Metadaten aus der offentlichen OpenRouter-API. Preise in USD pro 1M Tokens.

Modell	Organisation	Kontext	Eingabe $/1M	Ausgabe $/1M	Wissensstand
Auto Router (Beta)	openrouter	2,000,000	$-1,000,000	$-1,000,000
Pareto Code Router	openrouter	2,000,000	$-1,000,000	$-1,000,000
SpaceXAI: Grok 4.20 Multi-Agent	x-ai	2,000,000	$1.25	$2.5	2025-09-01
SpaceXAI: Grok 4.20	x-ai	2,000,000	$1.25	$2.5	2025-09-01
Auto Router	openrouter	2,000,000	$-1,000,000	$-1,000,000
DeepSeek V4 Flash Latest	~deepseek	1,310,720	$0.04	$0.08
DeepSeek: DeepSeek V4 Flash 0731	deepseek	1,310,720	$0.14	$0.28
Meta: Llama 4 Scout	meta-llama	1,310,720	$0.1	$0.3	2024-08-31
OpenAI: GPT-5.6 Luna Pro	openai	1,050,000	$0.2	$1.2	2026-02-16
OpenAI: GPT-5.6 Luna Pro (batch)	openai	1,050,000	$0.1	$0.6	2026-02-16
OpenAI: GPT-5.6 Luna	openai	1,050,000	$0.2	$1.2	2026-02-16
OpenAI: GPT-5.6 Luna (batch)	openai	1,050,000	$0.1	$0.6	2026-02-16
OpenAI: GPT-5.6 Terra Pro	openai	1,050,000	$2	$12	2026-02-16
OpenAI: GPT-5.6 Terra Pro (batch)	openai	1,050,000	$1	$6	2026-02-16
OpenAI: GPT-5.6 Terra	openai	1,050,000	$2	$12	2026-02-16
OpenAI: GPT-5.6 Terra (batch)	openai	1,050,000	$1	$6	2026-02-16
OpenAI: GPT-5.6 Sol Pro	openai	1,050,000	$2	$10	2026-02-16
OpenAI: GPT-5.6 Sol Pro (batch)	openai	1,050,000	$1	$5	2026-02-16
OpenAI: GPT-5.6 Sol	openai	1,050,000	$2	$10	2026-02-16
OpenAI: GPT-5.6 Sol (batch)	openai	1,050,000	$1	$5	2026-02-16

Letzte Anderungen

Die Anderungsverfolgung beginnt mit dem nachsten taglichen Snapshot. Rang- und Wertbewegungen werden hier gelistet.

Quellen und Methodik

Die Ranglisten werden aus offenen Community-Bewertungen aggregiert. Elo-Werte, Konfidenzintervalle und Stimmen stammen von LMArena (Community-Votings in direkten Modell-Duellen, als offenes Dataset veroffentlicht). Preise und Kontext-Metadaten stammen aus der offentlichen OpenRouter-API. Wikiprompt erstellt taglich einen Snapshot und bewahrt die Historie; eigene Evaluationen fuhren wir nicht durch.