Text-Arena

Von Wikiprompt, der freien Prompt-Enzyklopadie

Community-Elo-Rangliste, taglich aus LMArena-Duellen aggregiert. Zuerst die Gesamt-Arena, dann die Aufschlusselung nach Kategorie.

Zuletzt aktualisiert: 2026-10-13 · 215 Modelle

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
4	claude-opus-5-max	anthropic	1,507	1,502 / 1,512	30,569	Proprietary
5	claude-opus-4-6-high	anthropic	1,503	1,500 / 1,506	79,415	Proprietary
6	claude-opus-5-high	anthropic	1,503	1,499 / 1,506	62,934	Proprietary
7	gemini-3.8-flash-high	google	1,499	1,494 / 1,504	31,437	Proprietary
8	claude-opus-4-6	anthropic	1,498	1,495 / 1,501	84,095	Proprietary
10	claude-fable-5-high	anthropic	1,491	1,487 / 1,496	40,026	Proprietary
11	claude-opus-4-7-high	anthropic	1,490	1,486 / 1,493	65,192	Proprietary
13	gemini-3.7-flash-high	google	1,486	1,481 / 1,491	24,173	Proprietary
14	qwen3.8-max	alibaba	1,483	1,478 / 1,488	25,378	Proprietary
15	claude-opus-4-7	anthropic	1,483	1,479 / 1,487	66,315	Proprietary
17	gemini-3.5-flash-high	google	1,482	1,478 / 1,486	48,533	Proprietary
18	gemini-3.1-pro-preview	google	1,481	1,478 / 1,484	124,675	Proprietary
19	gemini-3-pro	google	1,479	1,476 / 1,483	42,078	Proprietary
20	gemini-3.6-flash-high	google	1,479	1,474 / 1,483	36,172	Proprietary
21	muse-spark-1.1	meta	1,479	1,474 / 1,483	39,847	Proprietary
22	gemini-3.5-flash-medium	google	1,477	1,473 / 1,482	47,339	Proprietary
24	kimi-k3-max	moonshot	1,476	1,471 / 1,480	30,351	Kimi K3 license
26	gpt-5.5-high	openai	1,472	1,468 / 1,475	69,437	Proprietary
29	glm-5.3-flash	zai	1,471	1,466 / 1,476	27,678	MIT
30	qwen3.5-max-preview	alibaba	1,470	1,466 / 1,475	22,624	Proprietary
31	glm-5.2-max	zai	1,470	1,466 / 1,474	47,521	MIT
32	gpt-5.4-high	openai	1,469	1,465 / 1,473	64,844	Proprietary
33	ernie-5.1	baidu	1,468	1,463 / 1,472	39,536	Proprietary
34	gpt-5.5	openai	1,467	1,463 / 1,470	71,047	Proprietary
35	gemini-3-flash	google	1,466	1,461 / 1,470	31,337	Proprietary
36	mimo-v2.5-pro	xiaomi	1,465	1,462 / 1,469	73,197	MIT
38	glm-5.1	zai	1,461	1,458 / 1,465	60,592	MIT
39	claude-opus-4-8-high	anthropic	1,461	1,457 / 1,465	64,177	Proprietary
40	claude-sonnet-4-6	anthropic	1,458	1,454 / 1,461	70,971	Proprietary
41	gemini-2.5-pro	google	1,458	1,455 / 1,460	125,379	Proprietary
42	gpt-5.6-sol-xhigh	openai	1,457	1,453 / 1,462	38,490	Proprietary
43	kimi-k2.6	moonshot	1,455	1,451 / 1,460	40,066	Modified MIT
45	qwen3.7-plus	alibaba	1,455	1,450 / 1,459	42,073	Proprietary
46	claude-opus-4-8	anthropic	1,454	1,450 / 1,458	65,259	Proprietary
47	gpt-5.4	openai	1,452	1,448 / 1,456	67,932	Proprietary
48	deepseek-v4-pro	deepseek	1,451	1,447 / 1,455	57,657	MIT
49	claude-opus-4-5-20251101	anthropic	1,451	1,448 / 1,454	72,952	Proprietary
50	grok-4.20-beta-0309-reasoning	xai	1,451	1,447 / 1,454	66,524	Proprietary
51	grok-4.20-multi-agent-beta-0309	xai	1,450	1,447 / 1,454	65,008	Proprietary
53	claude-opus-4-5-20251101-high-32k	anthropic	1,448	1,444 / 1,452	37,527	Proprietary
54	dola-seed-2.0-pro	bytedance	1,448	1,445 / 1,452	79,195	Proprietary
55	grok-4.5	xai	1,448	1,444 / 1,452	39,953	Proprietary
57	gpt-5.6-terra-xhigh	openai	1,447	1,442 / 1,451	40,278	Proprietary
59	glm-5	zai	1,446	1,442 / 1,450	29,292	MIT
61	kimi-k2.5-thinking	moonshot	1,445	1,442 / 1,448	74,811	Modified MIT
62	deepseek-v4-pro-high-preview	deepseek	1,445	1,441 / 1,449	54,976	MIT
63	ernie-5.0-0110	baidu	1,445	1,441 / 1,448	36,525	Proprietary
64	grok-4.20-beta1	xai	1,445	1,440 / 1,449	27,928	Proprietary
67	gpt-5.1-high	openai	1,443	1,439 / 1,446	41,674	Proprietary
69	gemini-3-flash (thinking-minimal)	google	1,442	1,439 / 1,445	91,105	Proprietary
70	claude-sonnet-5-high	anthropic	1,442	1,438 / 1,446	47,576	Proprietary
72	inkling	thinky	1,441	1,437 / 1,446	37,744	Apache 2.0
73	qwen3.8-27b	alibaba	1,441	1,436 / 1,446	20,711	Apache 2.0
75	glm-4.6	zai	1,440	1,436 / 1,444	35,828	MIT
76	qwen3-max-preview	alibaba	1,439	1,434 / 1,443	27,379	Proprietary
78	gpt-5.2-chat-latest-20260210	openai	1,439	1,435 / 1,443	36,007	Proprietary
79	claude-sonnet-4-5-20250929	anthropic	1,439	1,436 / 1,441	82,735	Proprietary
80	qwen3.5-397b-a17b	alibaba	1,438	1,435 / 1,441	91,190	Apache 2.0
82	qwen3.6-plus	alibaba	1,437	1,432 / 1,441	48,208	Proprietary
83	grok-4.1-thinking	xai	1,436	1,433 / 1,440	66,511	Proprietary
84	grok-4.1	xai	1,436	1,433 / 1,439	68,682	Proprietary
85	mimo-v2-pro	xiaomi	1,436	1,431 / 1,441	25,447	Proprietary
87	gemini-3.5-flash-lite	google	1,435	1,430 / 1,439	35,892	Proprietary
88	claude-sonnet-4-5-20250929-high-32k	anthropic	1,435	1,432 / 1,437	83,973	Proprietary
90	minimax-m3	minimax	1,433	1,429 / 1,436	61,220	MiniMax Community License
91	deepseek-v4-flash	deepseek	1,432	1,428 / 1,436	52,047	MIT
92	gpt-5.6-luna-xhigh	openai	1,430	1,426 / 1,435	40,917	Proprietary
93	glm-4.5	zai	1,430	1,425 / 1,435	23,803	MIT
95	chatgpt-4o-latest-20250326	openai	1,429	1,426 / 1,431	81,927	Proprietary
96	grok-4.6-high	xai	1,428	1,423 / 1,433	26,115	Proprietary
97	mistral-large-3	mistral	1,428	1,425 / 1,430	81,759	Apache 2.0
99	mimo-v2.5	xiaomi	1,428	1,423 / 1,432	47,402	MIT
101	longcat-flash-chat-2602-exp	meituan	1,427	1,422 / 1,431	29,306	Proprietary
102	grok-3-preview-02-24	xai	1,426	1,421 / 1,430	32,502	Proprietary
104	deepseek-v3.2	deepseek	1,425	1,421 / 1,428	48,114	MIT
105	deepseek-v4-flash-high-preview	deepseek	1,424	1,420 / 1,428	51,859	MIT
106	mistral-medium-2508	mistral	1,424	1,422 / 1,427	95,354	Proprietary
107	mimo-v2-omni	xiaomi	1,423	1,418 / 1,429	20,667	Proprietary
109	gpt-5.1	openai	1,422	1,419 / 1,426	44,441	Proprietary
113	deepseek-v3.2-thinking	deepseek	1,420	1,416 / 1,424	42,076	MIT
117	claude-opus-4-1-20250805-thinking-16k	anthropic	1,419	1,416 / 1,423	49,555	Proprietary
118	qwen3-235b-a22b-instruct-2507	alibaba	1,419	1,417 / 1,422	98,167	Apache 2.0
119	gpt-5.5-instant	openai	1,419	1,414 / 1,424	27,187	Proprietary
121	claude-opus-4-1-20250805	anthropic	1,419	1,416 / 1,422	77,252	Proprietary
123	qwen3.5-122b-a10b	alibaba	1,417	1,413 / 1,422	29,734	Apache 2.0
125	qwen3-next-80b-a3b-instruct	alibaba	1,417	1,412 / 1,422	22,763	Apache 2.0
126	gemini-2.5-flash	google	1,417	1,415 / 1,419	125,562	Proprietary
128	gpt-5.2-high	openai	1,416	1,413 / 1,420	49,685	Proprietary
129	gemini-3.1-flash-lite-preview	google	1,416	1,412 / 1,419	64,257	Proprietary
131	amazon-nova-experimental-chat-11-10	amazon	1,415	1,411 / 1,419	26,059	Proprietary
132	kimi-k2-thinking-turbo	moonshot	1,414	1,411 / 1,418	63,390	Modified MIT
133	Inkling Small	thinky	1,414	1,409 / 1,418	29,528	Apache 2.0
135	gpt-5.2	openai	1,412	1,409 / 1,415	83,928	Proprietary
136	gpt-5.4-mini-high	openai	1,411	1,408 / 1,415	63,493	Proprietary
137	grok-4-0709	xai	1,411	1,408 / 1,415	39,691	Proprietary
138	mimo-v2-flash (non-thinking)	xiaomi	1,411	1,408 / 1,414	48,117	MIT
139	o3-2025-04-16	openai	1,410	1,406 / 1,413	58,913	Proprietary
140	qwen3.5-27b	alibaba	1,409	1,405 / 1,413	28,677	Apache 2.0
141	grok-4-1-fast-reasoning	xai	1,408	1,405 / 1,411	57,574	Proprietary
143	gemini-2.5-flash-preview-09-2025	google	1,406	1,402 / 1,410	32,993	Proprietary

Nach Kategorie

Exclude ties

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
4	claude-opus-5-max	anthropic	1,525	1,518 / 1,531	23,001	Proprietary
5	claude-opus-4-6-high	anthropic	1,519	1,514 / 1,523	60,661	Proprietary
6	claude-opus-5-high	anthropic	1,519	1,514 / 1,524	47,524	Proprietary
7	gemini-3.8-flash-high	google	1,515	1,508 / 1,521	23,209	Proprietary
8	claude-opus-4-6	anthropic	1,514	1,509 / 1,518	63,896	Proprietary
10	claude-fable-5-high	anthropic	1,504	1,498 / 1,510	30,169	Proprietary
12	claude-opus-4-7-high	anthropic	1,502	1,497 / 1,506	49,710	Proprietary
15	claude-opus-4-7	anthropic	1,492	1,488 / 1,497	50,743	Proprietary
17	gemini-3-pro	google	1,491	1,486 / 1,496	30,198	Proprietary
18	gemini-3.5-flash-high	google	1,491	1,486 / 1,496	36,578	Proprietary
19	gemini-3.1-pro-preview	google	1,490	1,486 / 1,494	93,737	Proprietary
20	gemini-3.6-flash-high	google	1,487	1,481 / 1,493	26,959	Proprietary
21	muse-spark-1.1	meta	1,486	1,481 / 1,492	29,580	Proprietary
22	gemini-3.5-flash-medium	google	1,486	1,480 / 1,491	35,517	Proprietary
23	kimi-k3-max	moonshot	1,483	1,477 / 1,489	22,393	Kimi K3 license

Non english

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
5	claude-opus-5-high	anthropic	1,496	1,491 / 1,500	37,248	Proprietary
7	claude-opus-4-6-high	anthropic	1,489	1,485 / 1,493	44,368	Proprietary
8	claude-opus-4-6	anthropic	1,486	1,482 / 1,490	46,487	Proprietary
11	claude-fable-5-high	anthropic	1,481	1,475 / 1,486	22,870	Proprietary
12	claude-opus-4-7-high	anthropic	1,480	1,476 / 1,485	34,989	Proprietary
14	gemini-3.1-pro-preview	google	1,477	1,473 / 1,480	69,701	Proprietary
15	gemini-3.5-flash-high	google	1,476	1,471 / 1,480	27,943	Proprietary
17	claude-opus-4-7	anthropic	1,474	1,470 / 1,479	35,739	Proprietary
19	gemini-3-pro	google	1,474	1,469 / 1,479	25,129	Proprietary
20	muse-spark-1.1	meta	1,472	1,467 / 1,477	23,680	Proprietary
22	gemini-3.5-flash-medium	google	1,471	1,466 / 1,476	27,263	Proprietary
23	gemini-3.6-flash-high	google	1,469	1,464 / 1,475	20,993	Proprietary
24	gpt-5.5-high	openai	1,467	1,463 / 1,472	37,875	Proprietary
27	gpt-5.4-high	openai	1,465	1,460 / 1,470	35,499	Proprietary
30	gpt-5.5	openai	1,459	1,455 / 1,464	38,800	Proprietary

Hard prompts

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
3	claude-opus-4-6-high	anthropic	1,527	1,523 / 1,531	50,602	Proprietary
6	claude-opus-4-6	anthropic	1,524	1,520 / 1,528	54,602	Proprietary
7	claude-opus-5-high	anthropic	1,522	1,518 / 1,527	41,192	Proprietary
10	claude-fable-5-high	anthropic	1,508	1,503 / 1,513	26,112	Proprietary
11	claude-opus-4-7-high	anthropic	1,506	1,501 / 1,510	43,711	Proprietary
13	claude-opus-4-7	anthropic	1,500	1,496 / 1,504	44,480	Proprietary
20	gpt-5.5-high	openai	1,489	1,485 / 1,493	45,609	Proprietary
21	gemini-3.5-flash-high	google	1,488	1,483 / 1,492	32,427	Proprietary
22	mimo-v2.5-pro	xiaomi	1,488	1,483 / 1,492	47,906	MIT
24	muse-spark-1.1	meta	1,486	1,481 / 1,491	26,393	Proprietary
25	gpt-5.5	openai	1,486	1,481 / 1,490	47,348	Proprietary
26	gemini-3.1-pro-preview	google	1,485	1,481 / 1,489	81,091	Proprietary
27	gemini-3.6-flash-high	google	1,485	1,480 / 1,490	24,180	Proprietary
28	gpt-5.4-high	openai	1,485	1,480 / 1,489	42,194	Proprietary
29	claude-sonnet-4-6	anthropic	1,484	1,480 / 1,489	46,250	Proprietary

English

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
3	claude-opus-4-6-high	anthropic	1,513	1,508 / 1,517	35,044	Proprietary
4	claude-opus-4-6	anthropic	1,506	1,502 / 1,511	37,603	Proprietary
8	claude-opus-5-high	anthropic	1,503	1,498 / 1,508	25,673	Proprietary
11	claude-opus-4-7-high	anthropic	1,496	1,491 / 1,501	30,201	Proprietary
15	claude-opus-4-7	anthropic	1,488	1,483 / 1,493	30,576	Proprietary
23	gemini-3.1-pro-preview	google	1,479	1,475 / 1,483	54,965	Proprietary
24	mimo-v2.5-pro	xiaomi	1,478	1,474 / 1,483	30,746	MIT
31	glm-5.1	zai	1,475	1,470 / 1,480	26,109	MIT
35	claude-sonnet-4-6	anthropic	1,472	1,468 / 1,477	31,966	Proprietary
36	gpt-5.5-high	openai	1,470	1,466 / 1,475	31,561	Proprietary
38	gpt-5.5	openai	1,469	1,464 / 1,474	32,246	Proprietary
39	claude-opus-4-8-high	anthropic	1,468	1,463 / 1,473	28,032	Proprietary
41	gpt-5.4-high	openai	1,467	1,462 / 1,472	29,343	Proprietary
42	claude-opus-4-5-20251101	anthropic	1,461	1,456 / 1,465	31,232	Proprietary
44	claude-opus-4-8	anthropic	1,460	1,455 / 1,465	28,751	Proprietary

Instruction following

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
3	claude-opus-4-6-high	anthropic	1,523	1,518 / 1,529	25,594	Proprietary
6	claude-opus-5-high	anthropic	1,516	1,510 / 1,521	22,294	Proprietary
7	claude-opus-4-6	anthropic	1,511	1,506 / 1,516	28,177	Proprietary
9	claude-opus-4-7-high	anthropic	1,498	1,492 / 1,503	22,790	Proprietary
13	claude-opus-4-7	anthropic	1,489	1,483 / 1,494	23,398	Proprietary
18	gpt-5.5-high	openai	1,479	1,473 / 1,484	24,045	Proprietary
21	mimo-v2.5-pro	xiaomi	1,477	1,472 / 1,482	24,552	MIT
24	claude-opus-4-8-high	anthropic	1,476	1,471 / 1,481	22,729	Proprietary
25	claude-sonnet-4-6	anthropic	1,475	1,470 / 1,481	23,721	Proprietary
26	gpt-5.5	openai	1,475	1,470 / 1,480	24,853	Proprietary
28	claude-opus-4-5-20251101	anthropic	1,473	1,468 / 1,478	21,858	Proprietary
29	gpt-5.4-high	openai	1,469	1,464 / 1,475	21,925	Proprietary
33	gemini-3.1-pro-preview	google	1,466	1,462 / 1,470	42,594	Proprietary
37	claude-opus-4-8	anthropic	1,463	1,458 / 1,468	23,318	Proprietary
42	claude-sonnet-4-5-20250929	anthropic	1,459	1,454 / 1,464	24,390	Proprietary

Industry software and it services

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
4	claude-opus-4-6	anthropic	1,528	1,524 / 1,533	32,840	Proprietary
5	claude-opus-5-high	anthropic	1,528	1,522 / 1,533	23,515	Proprietary
7	claude-opus-4-6-high	anthropic	1,527	1,522 / 1,532	30,206	Proprietary
9	claude-opus-4-7-high	anthropic	1,516	1,511 / 1,521	26,190	Proprietary
13	claude-opus-4-7	anthropic	1,506	1,501 / 1,512	26,523	Proprietary
23	mimo-v2.5-pro	xiaomi	1,496	1,491 / 1,501	28,811	MIT
26	gpt-5.5-high	openai	1,493	1,488 / 1,498	27,465	Proprietary
30	gpt-5.4-high	openai	1,491	1,486 / 1,497	25,484	Proprietary
31	claude-sonnet-4-6	anthropic	1,491	1,486 / 1,496	27,754	Proprietary
33	claude-opus-4-8-high	anthropic	1,488	1,483 / 1,493	25,152	Proprietary
34	gemini-3.1-pro-preview	google	1,487	1,483 / 1,491	49,083	Proprietary
35	gpt-5.5	openai	1,487	1,482 / 1,492	28,336	Proprietary
43	claude-opus-4-5-20251101	anthropic	1,483	1,479 / 1,488	26,908	Proprietary
44	claude-opus-4-8	anthropic	1,483	1,478 / 1,488	25,745	Proprietary
45	glm-5.1	zai	1,483	1,478 / 1,487	23,890	MIT

Longer query

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
4	claude-opus-4-6-high	anthropic	1,519	1,515 / 1,524	33,635	Proprietary
5	claude-opus-4-6	anthropic	1,516	1,511 / 1,521	36,580	Proprietary
7	claude-opus-5-high	anthropic	1,514	1,509 / 1,520	29,739	Proprietary
10	claude-opus-4-7-high	anthropic	1,505	1,500 / 1,510	30,137	Proprietary
12	claude-opus-4-7	anthropic	1,499	1,494 / 1,504	30,910	Proprietary
18	gpt-5.5-high	openai	1,484	1,479 / 1,489	32,057	Proprietary
19	claude-opus-4-8-high	anthropic	1,483	1,478 / 1,488	30,277	Proprietary
20	gemini-3.1-pro-preview	google	1,483	1,479 / 1,487	55,079	Proprietary
21	mimo-v2.5-pro	xiaomi	1,483	1,478 / 1,488	32,625	MIT
23	gemini-3.5-flash-high	google	1,482	1,477 / 1,488	22,849	Proprietary
26	gpt-5.5	openai	1,482	1,477 / 1,487	33,450	Proprietary
28	claude-opus-4-8	anthropic	1,480	1,475 / 1,485	30,920	Proprietary
29	claude-opus-4-5-20251101	anthropic	1,479	1,475 / 1,484	24,293	Proprietary
30	glm-5.2-max	zai	1,479	1,474 / 1,484	21,900	MIT
31	claude-sonnet-4-6	anthropic	1,479	1,474 / 1,484	31,104	Proprietary

Hard prompts english

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
3	claude-opus-4-6-high	anthropic	1,532	1,527 / 1,538	22,800	Proprietary
4	claude-opus-4-6	anthropic	1,528	1,523 / 1,533	24,940	Proprietary
10	claude-opus-4-7-high	anthropic	1,508	1,502 / 1,514	20,853	Proprietary
14	claude-opus-4-7	anthropic	1,501	1,496 / 1,507	21,190	Proprietary
18	mimo-v2.5-pro	xiaomi	1,495	1,490 / 1,501	20,787	MIT
20	claude-sonnet-4-6	anthropic	1,493	1,488 / 1,499	21,348	Proprietary
27	gpt-5.5	openai	1,483	1,478 / 1,489	21,971	Proprietary
29	gpt-5.5-high	openai	1,483	1,477 / 1,488	21,239	Proprietary
35	gemini-3.1-pro-preview	google	1,481	1,476 / 1,485	36,546	Proprietary
46	claude-sonnet-4-5-20250929-high-32k	anthropic	1,472	1,467 / 1,476	21,152	Proprietary
48	claude-sonnet-4-5-20250929	anthropic	1,470	1,465 / 1,475	21,311	Proprietary
53	gpt-5.4	openai	1,464	1,458 / 1,469	21,104	Proprietary
63	kimi-k2.5-thinking	moonshot	1,460	1,455 / 1,465	21,063	Modified MIT
74	grok-4.20-beta-0309-reasoning	xai	1,455	1,449 / 1,460	20,682	Proprietary
78	gemini-2.5-pro	google	1,452	1,448 / 1,457	28,958	Proprietary

Industry writing and literature and language

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
8	claude-opus-4-6	anthropic	1,493	1,488 / 1,498	20,865	Proprietary
13	gemini-3.1-pro-preview	google	1,480	1,475 / 1,485	31,816	Proprietary
35	gemini-2.5-pro	google	1,454	1,450 / 1,458	28,281	Proprietary
57	gemini-3-flash (thinking-minimal)	google	1,436	1,431 / 1,441	22,080	Proprietary
83	qwen3.5-397b-a17b	alibaba	1,415	1,410 / 1,420	22,473	Apache 2.0
106	gemini-2.5-flash	google	1,405	1,401 / 1,409	28,464	Proprietary
121	mistral-medium-2508	mistral	1,395	1,390 / 1,400	21,945	Proprietary
129	qwen3-235b-a22b-instruct-2507	alibaba	1,390	1,386 / 1,394	22,168	Apache 2.0
138	claude-haiku-4-5-20251001	anthropic	1,387	1,383 / 1,391	35,669	Proprietary
214	claude-3-5-sonnet-20241022	anthropic	1,314	1,309 / 1,319	21,821	Proprietary
230	gpt-4o-2024-05-13	openai	1,298	1,292 / 1,304	29,959	Proprietary
242	gemini-1.5-pro-001	google	1,289	1,282 / 1,296	20,950	Proprietary
250	claude-3-5-sonnet-20240620	anthropic	1,280	1,274 / 1,286	21,916	Proprietary
252	gpt-4-turbo-2024-04-09	openai	1,279	1,272 / 1,285	24,529	Proprietary
264	claude-3-opus-20240229	anthropic	1,269	1,263 / 1,274	49,929	Proprietary

Coding

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
3	claude-opus-4-6	anthropic	1,535	1,530 / 1,541	23,351	Proprietary
6	claude-opus-4-6-high	anthropic	1,533	1,528 / 1,539	20,617	Proprietary
46	gemini-3.1-pro-preview	google	1,484	1,480 / 1,489	34,338	Proprietary
60	kimi-k2.5-thinking	moonshot	1,474	1,469 / 1,479	20,766	Modified MIT
64	dola-seed-2.0-pro	bytedance	1,472	1,467 / 1,477	22,064	Proprietary
77	qwen3.5-397b-a17b	alibaba	1,465	1,460 / 1,469	25,953	Apache 2.0
90	minimax-m2.7	minimax	1,454	1,449 / 1,459	23,483	Modified MIT
95	claude-haiku-4-5-20251001	anthropic	1,453	1,449 / 1,457	37,782	Proprietary
98	gemini-2.5-pro	google	1,452	1,447 / 1,456	26,960	Proprietary
109	qwen3-235b-a22b-instruct-2507	alibaba	1,445	1,440 / 1,449	21,747	Apache 2.0
125	gemini-3-flash (thinking-minimal)	google	1,436	1,431 / 1,441	23,993	Proprietary
129	mistral-medium-2508	mistral	1,434	1,429 / 1,438	21,576	Proprietary
133	gpt-5.2	openai	1,432	1,427 / 1,437	22,142	Proprietary
143	gemini-2.5-flash	google	1,424	1,419 / 1,428	26,380	Proprietary
285	claude-3-opus-20240229	anthropic	1,264	1,258 / 1,270	33,748	Proprietary

Industry entertainment and sports and media

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
14	gemini-3.1-pro-preview	google	1,466	1,461 / 1,471	28,804	Proprietary
36	gemini-2.5-pro	google	1,441	1,437 / 1,446	23,337	Proprietary
99	qwen3.5-397b-a17b	alibaba	1,398	1,393 / 1,403	20,604	Apache 2.0
110	gemini-2.5-flash	google	1,394	1,389 / 1,398	23,202	Proprietary
142	claude-haiku-4-5-20251001	anthropic	1,369	1,365 / 1,374	31,491	Proprietary
287	claude-3-opus-20240229	anthropic	1,220	1,214 / 1,226	29,359	Proprietary
301	llama-3-70b-instruct	meta	1,196	1,188 / 1,203	23,202	Llama 3 Community

Industry life and physical and social science

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
18	gemini-3.1-pro-preview	google	1,497	1,492 / 1,503	20,792	Proprietary
34	gemini-2.5-pro	google	1,480	1,475 / 1,485	20,888	Proprietary
119	gemini-2.5-flash	google	1,433	1,428 / 1,438	20,589	Proprietary
160	claude-haiku-4-5-20251001	anthropic	1,405	1,401 / 1,410	23,848	Proprietary
289	claude-3-opus-20240229	anthropic	1,254	1,248 / 1,260	33,790	Proprietary
307	llama-3-70b-instruct	meta	1,226	1,218 / 1,233	25,903	Llama 3 Community

Multi turn

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
15	gemini-3.1-pro-preview	google	1,488	1,482 / 1,493	21,223	Proprietary
61	gemini-2.5-pro	google	1,453	1,448 / 1,457	21,196	Proprietary
136	claude-haiku-4-5-20251001	anthropic	1,409	1,405 / 1,414	25,458	Proprietary
139	gemini-2.5-flash	google	1,408	1,403 / 1,412	21,715	Proprietary
267	claude-3-opus-20240229	anthropic	1,275	1,269 / 1,281	31,134	Proprietary
298	llama-3-70b-instruct	meta	1,223	1,216 / 1,230	21,421	Llama 3 Community

Industry business and management and financial operations

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
31	gemini-3.1-pro-preview	google	1,460	1,455 / 1,465	24,228	Proprietary
55	gemini-2.5-pro	google	1,439	1,435 / 1,444	22,807	Proprietary
132	gemini-2.5-flash	google	1,404	1,399 / 1,408	22,752	Proprietary
136	claude-haiku-4-5-20251001	anthropic	1,400	1,395 / 1,404	28,280	Proprietary
292	claude-3-opus-20240229	anthropic	1,222	1,215 / 1,229	21,697	Proprietary

Creative writing

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
13	gemini-3.1-pro-preview	google	1,482	1,477 / 1,487	22,975	Proprietary
140	claude-haiku-4-5-20251001	anthropic	1,372	1,367 / 1,376	24,835	Proprietary
283	claude-3-opus-20240229	anthropic	1,235	1,228 / 1,241	28,395	Proprietary
298	llama-3-70b-instruct	meta	1,210	1,202 / 1,217	22,753	Llama 3 Community

Math

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
258	claude-3-opus-20240229	anthropic	1,272	1,266 / 1,279	25,769	Proprietary
296	llama-3-70b-instruct	meta	1,218	1,210 / 1,225	20,941	Llama 3 Community

Chinese

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
270	claude-3-opus-20240229	anthropic	1,248	1,240 / 1,256	23,348	Proprietary

Industry mathematical

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
272	claude-3-opus-20240229	anthropic	1,264	1,257 / 1,271	22,970	Proprietary

Russian

Rang	Modell	Organisation	Elo-Wert	95%-KI	Stimmen	Lizenz
248	claude-3-opus-20240229	anthropic	1,280	1,273 / 1,287	21,089	Proprietary

Siehe auch

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.