テキストアリーナ

フリーなプロンプト百科事典 Wikiprompt より

コミュニティEloランキング。LMArenaの対戦から毎日集計。総合アリーナの後にカテゴリ別の内訳を示します。

最終更新: 2026-08-24 · 211 モデル

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
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
35	gpt-5.6-sol-xhigh	openai	1,454	1,449 / 1,460	19,541	Proprietary
36	gpt-5.4	openai	1,453	1,449 / 1,456	63,659	Proprietary
37	grok-4.5	xai	1,452	1,447 / 1,457	22,030	Proprietary
38	claude-opus-4-8	anthropic	1,452	1,448 / 1,456	45,331	Proprietary
39	grok-4.20-beta-0309-reasoning	xai	1,451	1,447 / 1,455	62,272	Proprietary
40	deepseek-v4-pro	deepseek	1,451	1,447 / 1,455	54,263	MIT
41	grok-4.20-multi-agent-beta-0309	xai	1,450	1,446 / 1,454	60,864	Proprietary
42	claude-opus-4-5-20251101	anthropic	1,450	1,447 / 1,453	70,985	Proprietary
43	dola-seed-2.0-pro	bytedance	1,448	1,444 / 1,451	74,513	Proprietary
45	claude-opus-4-5-20251101-high-32k	anthropic	1,447	1,443 / 1,451	37,198	Proprietary
47	gpt-5.6-terra-xhigh	openai	1,446	1,441 / 1,451	20,216	Proprietary
48	glm-5	zai	1,445	1,441 / 1,450	27,850	MIT
49	kimi-k2.5-thinking	moonshot	1,445	1,442 / 1,449	70,943	Modified MIT
50	deepseek-v4-pro-high-preview	deepseek	1,445	1,441 / 1,449	51,642	MIT
52	ernie-5.0-0110	baidu	1,444	1,441 / 1,448	35,267	Proprietary
53	grok-4.20-beta1	xai	1,444	1,440 / 1,449	26,770	Proprietary
56	gemini-3-flash (thinking-minimal)	google	1,442	1,439 / 1,445	86,359	Proprietary
57	claude-sonnet-5-high	anthropic	1,442	1,437 / 1,447	27,366	Proprietary
59	gpt-5.1-high	openai	1,441	1,438 / 1,445	40,945	Proprietary
62	glm-4.6	zai	1,440	1,436 / 1,444	35,830	MIT
65	qwen3-max-preview	alibaba	1,439	1,435 / 1,444	27,838	Proprietary
66	gpt-5.2-chat-latest-20260210	openai	1,439	1,435 / 1,443	34,339	Proprietary
67	qwen3.5-397b-a17b	alibaba	1,438	1,435 / 1,442	70,207	Apache 2.0
68	claude-sonnet-4-5-20250929	anthropic	1,438	1,435 / 1,441	80,858	Proprietary
69	grok-4.1-thinking	xai	1,437	1,434 / 1,440	65,550	Proprietary
70	qwen3.6-plus	alibaba	1,437	1,433 / 1,441	45,376	Proprietary
72	mimo-v2-pro	xiaomi	1,437	1,432 / 1,441	24,397	Proprietary
74	grok-4.1	xai	1,436	1,433 / 1,440	67,767	Proprietary
76	minimax-m3	minimax	1,435	1,430 / 1,439	41,023	MiniMax Community License
78	claude-sonnet-4-5-20250929-high-32k	anthropic	1,433	1,431 / 1,436	82,473	Proprietary
79	deepseek-v4-flash	deepseek	1,432	1,427 / 1,436	49,001	MIT
80	glm-4.5	zai	1,429	1,425 / 1,434	24,403	MIT
82	chatgpt-4o-latest-20250326	openai	1,429	1,426 / 1,431	82,766	Proprietary
83	gpt-5.6-luna-xhigh	openai	1,429	1,423 / 1,434	20,693	Proprietary
84	mistral-large-3	mistral	1,428	1,425 / 1,431	62,644	Apache 2.0
86	mimo-v2.5	xiaomi	1,427	1,423 / 1,432	44,557	MIT
87	longcat-flash-chat-2602-exp	meituan	1,426	1,421 / 1,430	27,982	Proprietary
88	grok-3-preview-02-24	xai	1,425	1,421 / 1,429	32,941	Proprietary
89	mistral-medium-2508	mistral	1,425	1,422 / 1,428	94,016	Proprietary
90	deepseek-v3.2	deepseek	1,425	1,421 / 1,428	47,295	MIT
92	deepseek-v4-flash-high-preview	deepseek	1,424	1,420 / 1,428	48,679	MIT
94	mimo-v2-omni	xiaomi	1,422	1,417 / 1,428	19,434	Proprietary
95	gpt-5.1	openai	1,422	1,419 / 1,426	43,653	Proprietary
101	deepseek-v3.2-thinking	deepseek	1,420	1,416 / 1,423	41,123	MIT
103	gpt-5.5-instant	openai	1,420	1,414 / 1,425	25,863	Proprietary
104	qwen3-235b-a22b-instruct-2507	alibaba	1,419	1,417 / 1,422	97,398	Apache 2.0
106	qwen3-next-80b-a3b-instruct	alibaba	1,419	1,414 / 1,423	23,000	Apache 2.0
107	claude-opus-4-1-20250805-thinking-16k	anthropic	1,418	1,415 / 1,422	50,016	Proprietary
108	qwen3.5-122b-a10b	alibaba	1,418	1,414 / 1,422	28,413	Apache 2.0
109	claude-opus-4-1-20250805	anthropic	1,418	1,415 / 1,421	77,751	Proprietary
111	gemini-2.5-flash	google	1,417	1,415 / 1,420	124,731	Proprietary
114	gpt-5.2-high	openai	1,416	1,413 / 1,420	47,920	Proprietary
115	amazon-nova-experimental-chat-11-10	amazon	1,416	1,412 / 1,420	25,430	Proprietary
116	gemini-3.1-flash-lite-preview	google	1,415	1,411 / 1,418	60,594	Proprietary
117	kimi-k2-thinking-turbo	moonshot	1,414	1,411 / 1,417	62,107	Modified MIT
120	gpt-5.4-mini-high	openai	1,412	1,408 / 1,416	59,502	Proprietary
121	gpt-5.2	openai	1,412	1,409 / 1,415	79,397	Proprietary
123	mimo-v2-flash (non-thinking)	xiaomi	1,411	1,408 / 1,415	46,603	MIT
124	grok-4-0709	xai	1,410	1,406 / 1,414	41,530	Proprietary
125	o3-2025-04-16	openai	1,409	1,406 / 1,413	59,888	Proprietary
127	grok-4-1-fast-reasoning	xai	1,408	1,405 / 1,411	56,768	Proprietary
128	qwen3.5-27b	alibaba	1,408	1,403 / 1,412	27,282	Apache 2.0
129	gemini-2.5-flash-preview-09-2025	google	1,407	1,403 / 1,411	33,064	Proprietary
131	gpt-5-high	openai	1,406	1,401 / 1,410	32,081	Proprietary
132	minimax-m2.7	minimax	1,405	1,402 / 1,409	62,076	Modified MIT
134	step-3.5-flash	stepfun	1,404	1,400 / 1,407	57,417	Apache 2.0
135	gpt-5-chat	openai	1,404	1,399 / 1,408	31,681	Proprietary
139	grok-4-fast-reasoning	xai	1,398	1,393 / 1,403	18,811	Proprietary
140	qwen3.5-flash	alibaba	1,398	1,394 / 1,401	58,319	Proprietary
141	grok-4.3	xai	1,397	1,394 / 1,401	61,016	Proprietary
142	qwen3.5-35b-a3b	alibaba	1,396	1,391 / 1,400	29,097	Apache 2.0
143	claude-haiku-4-5-20251001	anthropic	1,395	1,392 / 1,397	122,469	Proprietary
146	qwen3-235b-a22b-no-thinking	alibaba	1,393	1,389 / 1,398	38,267	Apache 2.0
149	gpt-5.3-chat-latest	openai	1,388	1,383 / 1,392	32,832	Proprietary
150	qwen3-30b-a3b-instruct-2507	alibaba	1,384	1,379 / 1,389	23,828	Apache 2.0

カテゴリ別

Exclude ties

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-5-high	anthropic	1,520	1,513 / 1,526	21,104	Proprietary
3	claude-opus-4-6-high	anthropic	1,518	1,514 / 1,523	55,193	Proprietary
4	claude-opus-4-6	anthropic	1,513	1,508 / 1,517	58,007	Proprietary
6	claude-opus-4-7-high	anthropic	1,502	1,497 / 1,507	45,885	Proprietary
10	claude-opus-4-7	anthropic	1,491	1,486 / 1,497	46,791	Proprietary
11	gemini-3.5-flash-high	google	1,491	1,485 / 1,497	22,742	Proprietary
12	gemini-3-pro	google	1,491	1,486 / 1,496	29,784	Proprietary
13	gemini-3.1-pro-preview	google	1,489	1,485 / 1,493	74,559	Proprietary
17	gemini-3.5-flash-medium	google	1,482	1,476 / 1,489	21,290	Proprietary
22	gpt-5.5-high	openai	1,476	1,471 / 1,481	45,179	Proprietary
23	gpt-5.4-high	openai	1,474	1,469 / 1,479	46,454	Proprietary
24	gemini-3-flash	google	1,474	1,468 / 1,480	21,906	Proprietary
25	ernie-5.1	baidu	1,472	1,466 / 1,478	28,203	Proprietary
26	gpt-5.5	openai	1,469	1,464 / 1,474	46,477	Proprietary
27	glm-5.2-max	zai	1,468	1,462 / 1,474	22,741	MIT

English

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,512	1,508 / 1,517	33,024	Proprietary
2	claude-opus-4-6	anthropic	1,507	1,502 / 1,511	35,446	Proprietary
7	claude-opus-4-7-high	anthropic	1,495	1,490 / 1,500	28,124	Proprietary
11	claude-opus-4-7	anthropic	1,486	1,481 / 1,491	28,408	Proprietary
13	gemini-3-pro	google	1,480	1,475 / 1,485	19,033	Proprietary
16	mimo-v2.5-pro	xiaomi	1,480	1,474 / 1,485	23,554	MIT
19	gemini-3.1-pro-preview	google	1,478	1,474 / 1,482	45,728	Proprietary
22	glm-5.1	zai	1,475	1,470 / 1,481	19,039	MIT
24	claude-sonnet-4-6	anthropic	1,473	1,469 / 1,478	30,831	Proprietary
27	gpt-5.5-high	openai	1,469	1,464 / 1,474	27,318	Proprietary
28	gpt-5.4-high	openai	1,468	1,463 / 1,473	28,092	Proprietary
29	gpt-5.5	openai	1,467	1,462 / 1,472	27,996	Proprietary
30	claude-opus-4-8-high	anthropic	1,466	1,460 / 1,471	20,037	Proprietary
33	claude-opus-4-5-20251101	anthropic	1,461	1,457 / 1,465	33,201	Proprietary
34	deepseek-v4-pro	deepseek	1,459	1,454 / 1,465	23,965	MIT

Non english

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
3	claude-opus-4-6-high	anthropic	1,489	1,485 / 1,493	39,333	Proprietary
6	claude-opus-4-6	anthropic	1,485	1,480 / 1,489	40,915	Proprietary
7	claude-opus-4-7-high	anthropic	1,482	1,477 / 1,487	32,077	Proprietary
10	gemini-3.1-pro-preview	google	1,478	1,473 / 1,482	53,449	Proprietary
12	claude-opus-4-7	anthropic	1,474	1,470 / 1,479	32,896	Proprietary
13	gemini-3-pro	google	1,474	1,469 / 1,479	22,451	Proprietary
18	gpt-5.5-high	openai	1,468	1,463 / 1,473	32,223	Proprietary
20	gpt-5.4-high	openai	1,465	1,461 / 1,470	32,616	Proprietary
24	gpt-5.5	openai	1,459	1,454 / 1,464	32,897	Proprietary
26	ernie-5.1	baidu	1,455	1,449 / 1,460	20,083	Proprietary
28	gemini-2.5-pro	google	1,454	1,450 / 1,457	65,590	Proprietary
29	claude-opus-4-8-high	anthropic	1,452	1,447 / 1,457	24,636	Proprietary
30	glm-5.1	zai	1,451	1,446 / 1,456	23,226	MIT
31	gpt-5.4	openai	1,449	1,445 / 1,454	34,058	Proprietary
33	mimo-v2.5-pro	xiaomi	1,448	1,443 / 1,453	30,622	MIT

Hard prompts

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,527	1,523 / 1,531	45,860	Proprietary
4	claude-opus-4-6	anthropic	1,523	1,518 / 1,527	49,427	Proprietary
6	claude-opus-4-7-high	anthropic	1,506	1,501 / 1,510	40,289	Proprietary
7	claude-opus-4-7	anthropic	1,499	1,494 / 1,504	40,978	Proprietary
13	gemini-3.5-flash-high	google	1,489	1,484 / 1,494	20,131	Proprietary
14	gpt-5.5-high	openai	1,488	1,484 / 1,493	39,020	Proprietary
15	mimo-v2.5-pro	xiaomi	1,487	1,482 / 1,492	35,595	MIT
16	gpt-5.4-high	openai	1,486	1,481 / 1,491	39,351	Proprietary
19	claude-sonnet-4-6	anthropic	1,484	1,480 / 1,489	43,194	Proprietary
20	gemini-3.1-pro-preview	google	1,484	1,480 / 1,488	64,253	Proprietary
22	gpt-5.5	openai	1,483	1,479 / 1,488	40,463	Proprietary
23	gemini-3.5-flash-medium	google	1,483	1,477 / 1,488	19,160	Proprietary
24	claude-opus-4-8-high	anthropic	1,482	1,477 / 1,487	29,722	Proprietary
25	gemini-3-pro	google	1,482	1,477 / 1,487	22,649	Proprietary
27	ernie-5.1	baidu	1,481	1,476 / 1,486	24,053	Proprietary

Instruction following

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,523	1,518 / 1,528	23,022	Proprietary
4	claude-opus-4-6	anthropic	1,511	1,506 / 1,516	25,262	Proprietary
6	claude-opus-4-7-high	anthropic	1,498	1,492 / 1,503	20,889	Proprietary
7	claude-opus-4-7	anthropic	1,488	1,482 / 1,493	21,394	Proprietary
13	gpt-5.5-high	openai	1,478	1,473 / 1,484	20,395	Proprietary
15	claude-sonnet-4-6	anthropic	1,477	1,472 / 1,482	22,105	Proprietary
18	claude-opus-4-5-20251101	anthropic	1,472	1,467 / 1,477	20,889	Proprietary
19	gpt-5.5	openai	1,472	1,466 / 1,478	21,014	Proprietary
20	gpt-5.4-high	openai	1,470	1,465 / 1,476	20,315	Proprietary
25	gemini-3.1-pro-preview	google	1,466	1,462 / 1,471	33,383	Proprietary
29	claude-sonnet-4-5-20250929	anthropic	1,459	1,454 / 1,464	23,524	Proprietary
33	claude-sonnet-4-5-20250929-high-32k	anthropic	1,457	1,453 / 1,462	23,892	Proprietary
34	gpt-5.4	openai	1,455	1,450 / 1,461	21,774	Proprietary
50	gemini-2.5-pro	google	1,437	1,433 / 1,441	34,639	Proprietary
57	claude-opus-4-1-20250805	anthropic	1,433	1,428 / 1,438	20,685	Proprietary

Industry software and it services

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
2	claude-opus-4-6-high	anthropic	1,528	1,523 / 1,533	27,625	Proprietary
3	claude-opus-4-6	anthropic	1,527	1,522 / 1,532	30,007	Proprietary
5	claude-opus-4-7-high	anthropic	1,516	1,510 / 1,521	24,304	Proprietary
7	claude-opus-4-7	anthropic	1,506	1,501 / 1,511	24,528	Proprietary
17	mimo-v2.5-pro	xiaomi	1,492	1,487 / 1,498	21,587	MIT
19	gpt-5.5-high	openai	1,492	1,487 / 1,497	23,675	Proprietary
20	claude-sonnet-4-6	anthropic	1,492	1,486 / 1,497	26,025	Proprietary
21	gpt-5.4-high	openai	1,491	1,485 / 1,496	23,878	Proprietary
26	gemini-3.1-pro-preview	google	1,485	1,481 / 1,490	39,219	Proprietary
29	gpt-5.5	openai	1,484	1,479 / 1,490	24,330	Proprietary
32	claude-opus-4-5-20251101	anthropic	1,482	1,477 / 1,486	26,318	Proprietary
43	gpt-5.4	openai	1,474	1,469 / 1,480	25,336	Proprietary
44	dola-seed-2.0-pro	bytedance	1,474	1,469 / 1,478	29,269	Proprietary
45	claude-sonnet-4-5-20250929	anthropic	1,472	1,468 / 1,477	29,767	Proprietary
48	claude-sonnet-4-5-20250929-high-32k	anthropic	1,470	1,466 / 1,474	30,065	Proprietary

Longer query

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,521	1,515 / 1,526	29,848	Proprietary
3	claude-opus-4-6	anthropic	1,517	1,512 / 1,522	32,387	Proprietary
6	claude-opus-4-7-high	anthropic	1,505	1,500 / 1,510	27,249	Proprietary
7	claude-opus-4-7	anthropic	1,498	1,493 / 1,503	27,967	Proprietary
14	gemini-3.1-pro-preview	google	1,483	1,479 / 1,488	42,340	Proprietary
16	mimo-v2.5-pro	xiaomi	1,483	1,478 / 1,489	23,802	MIT
17	gpt-5.5-high	openai	1,483	1,478 / 1,488	26,815	Proprietary
18	claude-opus-4-8-high	anthropic	1,483	1,477 / 1,489	20,732	Proprietary
19	claude-sonnet-4-6	anthropic	1,480	1,475 / 1,485	28,487	Proprietary
20	claude-opus-4-8	anthropic	1,480	1,474 / 1,486	21,063	Proprietary
21	claude-opus-4-5-20251101	anthropic	1,480	1,475 / 1,485	22,958	Proprietary
22	gpt-5.5	openai	1,479	1,473 / 1,484	27,880	Proprietary
26	claude-sonnet-4-5-20250929	anthropic	1,476	1,471 / 1,481	25,280	Proprietary
29	gpt-5.4-high	openai	1,475	1,469 / 1,480	26,054	Proprietary
30	claude-sonnet-4-5-20250929-high-32k	anthropic	1,475	1,470 / 1,479	24,926	Proprietary

Hard prompts english

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,531	1,526 / 1,537	21,591	Proprietary
2	claude-opus-4-6	anthropic	1,527	1,522 / 1,532	23,696	Proprietary
6	claude-opus-4-7-high	anthropic	1,506	1,500 / 1,511	19,487	Proprietary
9	claude-opus-4-7	anthropic	1,500	1,495 / 1,506	19,672	Proprietary
12	claude-sonnet-4-6	anthropic	1,494	1,488 / 1,499	20,648	Proprietary
21	claude-opus-4-5-20251101	anthropic	1,481	1,476 / 1,486	20,279	Proprietary
24	gemini-3.1-pro-preview	google	1,480	1,475 / 1,485	30,653	Proprietary
26	gpt-5.4-high	openai	1,480	1,474 / 1,486	18,968	Proprietary
27	gpt-5.5	openai	1,480	1,474 / 1,485	19,173	Proprietary
32	claude-sonnet-4-5-20250929-high-32k	anthropic	1,474	1,469 / 1,478	23,202	Proprietary
37	claude-sonnet-4-5-20250929	anthropic	1,471	1,466 / 1,476	23,385	Proprietary
43	gpt-5.4	openai	1,464	1,458 / 1,469	20,294	Proprietary
48	kimi-k2.5-thinking	moonshot	1,460	1,455 / 1,465	20,882	Modified MIT
59	grok-4.20-beta-0309-reasoning	xai	1,454	1,449 / 1,460	19,815	Proprietary
65	gemini-2.5-pro	google	1,452	1,448 / 1,456	32,646	Proprietary

Industry writing and literature and language

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
8	gemini-3.1-pro-preview	google	1,480	1,475 / 1,486	24,434	Proprietary
30	gemini-2.5-pro	google	1,454	1,450 / 1,458	27,867	Proprietary
46	gemini-3-flash (thinking-minimal)	google	1,436	1,431 / 1,441	20,500	Proprietary
52	claude-sonnet-4-5-20250929-high-32k	anthropic	1,431	1,426 / 1,436	18,850	Proprietary
92	gemini-2.5-flash	google	1,407	1,402 / 1,411	28,147	Proprietary
106	mistral-medium-2508	mistral	1,395	1,391 / 1,400	21,446	Proprietary
110	gpt-5.2	openai	1,392	1,387 / 1,397	19,053	Proprietary
114	qwen3-235b-a22b-instruct-2507	alibaba	1,390	1,386 / 1,395	21,817	Apache 2.0
123	claude-haiku-4-5-20251001	anthropic	1,386	1,382 / 1,391	28,689	Proprietary
197	claude-3-5-sonnet-20241022	anthropic	1,313	1,308 / 1,318	21,910	Proprietary
212	gpt-4o-2024-05-13	openai	1,298	1,292 / 1,303	29,959	Proprietary
224	gemini-1.5-pro-001	google	1,289	1,282 / 1,295	20,950	Proprietary
233	claude-3-5-sonnet-20240620	anthropic	1,280	1,274 / 1,286	21,916	Proprietary
235	gpt-4-turbo-2024-04-09	openai	1,278	1,272 / 1,285	24,529	Proprietary
248	claude-3-opus-20240229	anthropic	1,268	1,263 / 1,274	49,929	Proprietary

Coding

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
1	claude-opus-4-6-high	anthropic	1,535	1,530 / 1,541	18,844	Proprietary
2	claude-opus-4-6	anthropic	1,534	1,528 / 1,539	21,288	Proprietary
26	claude-sonnet-4-5-20250929-high-32k	anthropic	1,488	1,483 / 1,493	19,352	Proprietary
32	claude-sonnet-4-5-20250929	anthropic	1,485	1,480 / 1,491	19,145	Proprietary
37	gemini-3.1-pro-preview	google	1,483	1,478 / 1,488	27,416	Proprietary
51	kimi-k2.5-thinking	moonshot	1,473	1,468 / 1,479	19,675	Modified MIT
54	dola-seed-2.0-pro	bytedance	1,472	1,467 / 1,477	20,798	Proprietary
63	qwen3.5-397b-a17b	alibaba	1,465	1,459 / 1,470	20,247	Apache 2.0
82	claude-haiku-4-5-20251001	anthropic	1,453	1,448 / 1,457	31,146	Proprietary
83	gemini-2.5-pro	google	1,452	1,448 / 1,457	26,633	Proprietary
92	qwen3-235b-a22b-instruct-2507	alibaba	1,445	1,440 / 1,449	21,350	Apache 2.0
105	gemini-3-flash (thinking-minimal)	google	1,437	1,432 / 1,442	22,675	Proprietary
110	mistral-medium-2508	mistral	1,435	1,430 / 1,439	21,127	Proprietary
116	gpt-5.2	openai	1,432	1,427 / 1,437	20,858	Proprietary
127	gemini-2.5-flash	google	1,424	1,419 / 1,428	25,967	Proprietary

Industry life and physical and social science

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
26	gemini-2.5-pro	google	1,480	1,475 / 1,485	20,602	Proprietary
102	gemini-2.5-flash	google	1,433	1,429 / 1,438	20,271	Proprietary
146	claude-haiku-4-5-20251001	anthropic	1,403	1,398 / 1,408	19,721	Proprietary
237	gpt-4o-2024-05-13	openai	1,295	1,288 / 1,302	19,017	Proprietary
269	claude-3-opus-20240229	anthropic	1,254	1,248 / 1,260	33,790	Proprietary
287	llama-3-70b-instruct	meta	1,226	1,219 / 1,233	25,903	Llama 3 Community
293	claude-3-sonnet-20240229	anthropic	1,209	1,202 / 1,217	19,089	Proprietary
303	claude-3-haiku-20240307	anthropic	1,179	1,171 / 1,186	20,565	Proprietary

Multi turn

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
48	gemini-2.5-pro	google	1,453	1,448 / 1,458	21,349	Proprietary
122	gemini-2.5-flash	google	1,409	1,404 / 1,413	21,782	Proprietary
123	claude-haiku-4-5-20251001	anthropic	1,408	1,404 / 1,413	21,815	Proprietary
223	gpt-4o-2024-05-13	openai	1,302	1,295 / 1,308	20,434	Proprietary
247	claude-3-opus-20240229	anthropic	1,275	1,269 / 1,281	31,134	Proprietary
278	llama-3-70b-instruct	meta	1,223	1,215 / 1,230	21,421	Llama 3 Community
294	claude-3-haiku-20240307	anthropic	1,190	1,183 / 1,197	19,344	Proprietary

Industry entertainment and sports and media

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
11	gemini-3.1-pro-preview	google	1,463	1,457 / 1,468	21,882	Proprietary
28	gemini-2.5-pro	google	1,440	1,436 / 1,445	22,956	Proprietary
96	gemini-2.5-flash	google	1,394	1,389 / 1,398	22,884	Proprietary
125	claude-haiku-4-5-20251001	anthropic	1,369	1,365 / 1,374	25,109	Proprietary
268	claude-3-opus-20240229	anthropic	1,220	1,214 / 1,226	29,359	Proprietary
281	llama-3-70b-instruct	meta	1,196	1,188 / 1,203	23,202	Llama 3 Community

Industry business and management and financial operations

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
25	gemini-3.1-pro-preview	google	1,459	1,453 / 1,464	19,582	Proprietary
46	gemini-2.5-pro	google	1,439	1,435 / 1,444	22,626	Proprietary
117	gemini-2.5-flash	google	1,403	1,398 / 1,407	22,520	Proprietary
126	claude-haiku-4-5-20251001	anthropic	1,398	1,393 / 1,403	23,885	Proprietary
272	claude-3-opus-20240229	anthropic	1,222	1,215 / 1,229	21,697	Proprietary

Creative writing

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
124	claude-haiku-4-5-20251001	anthropic	1,373	1,368 / 1,378	19,430	Proprietary
264	claude-3-opus-20240229	anthropic	1,235	1,228 / 1,241	28,395	Proprietary
279	llama-3-70b-instruct	meta	1,209	1,202 / 1,217	22,753	Llama 3 Community

Math

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
235	claude-3-opus-20240229	anthropic	1,273	1,266 / 1,279	25,769	Proprietary
273	llama-3-70b-instruct	meta	1,218	1,211 / 1,225	20,941	Llama 3 Community

Chinese

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
244	claude-3-opus-20240229	anthropic	1,247	1,239 / 1,255	23,348	Proprietary

Industry mathematical

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
246	claude-3-opus-20240229	anthropic	1,264	1,257 / 1,271	22,970	Proprietary

Russian

順位	モデル	組織	Eloスコア	95%信頼区間	投票数	ライセンス
228	claude-3-opus-20240229	anthropic	1,279	1,272 / 1,286	21,089	Proprietary

出典と方法論

ランキングはオープンなコミュニティ評価から集計しています。Eloスコア、信頼区間、投票数は LMArena（コミュニティ投票によるモデル対戦、オープンデータセットとして公開）に由来します。価格とコンテキストのメタデータは OpenRouter の公開APIから取得。Wikiprompt は毎日スナップショットを保存し履歴を保持します。独自の評価は行いません。