Arene developpement web

De Wikiprompt, l’encyclopedie libre des prompts

Classement Elo communautaire, agrege chaque jour depuis les duels LMArena. L’arene generale d’abord, puis le detail par categorie.

Derniere mise a jour: 2026-08-24 · 117 modeles

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
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
26	seed-2.1-pro-preview	bytedance	1,521	1,514 / 1,529	7,679	Proprietary
27	gpt-5.6-terra-xhigh (codex-harness)	openai	1,520	1,511 / 1,529	5,677	Proprietary
28	hy3	tencent	1,518	1,506 / 1,531	2,680	Apache 2.0
29	gpt-5.6-luna-xhigh (codex-harness)	openai	1,518	1,509 / 1,526	5,742	Proprietary
30	qwen3.7-max-20260517	alibaba	1,517	1,509 / 1,524	8,380	Proprietary
31	glm-5.1	zai	1,509	1,502 / 1,516	9,296	MIT
32	kimi-k2.6	moonshot	1,509	1,501 / 1,516	9,589	Modified MIT
33	gpt-5.5-xhigh (codex-harness)	openai	1,508	1,502 / 1,515	13,648	Proprietary
34	gemini-3.5-flash-high	google	1,499	1,491 / 1,507	7,559	Proprietary
35	claude-opus-4-5-20251101-high-32k	anthropic	1,494	1,486 / 1,503	10,617	Proprietary
36	gemini-3.5-flash-medium	google	1,490	1,483 / 1,497	10,038	Proprietary
37	minimax-m3	minimax	1,488	1,481 / 1,495	10,721	MiniMax Community License
38	gpt-5.5-high (codex-harness)	openai	1,486	1,480 / 1,492	15,630	Proprietary
39	qwen3.6-max-preview	alibaba	1,479	1,466 / 1,492	2,602	Proprietary
40	mimo-v2.5-pro	xiaomi	1,476	1,469 / 1,482	13,998	MIT
41	kimi-k2.7-code	moonshot	1,473	1,463 / 1,482	4,680	Modified MIT
42	claude-opus-4-5-20251101	anthropic	1,468	1,461 / 1,475	12,925	Proprietary
43	deepseek-v4-pro-high-preview	deepseek	1,464	1,457 / 1,470	12,409	MIT
44	gpt-5.4-high (codex-harness)	openai	1,463	1,443 / 1,482	1,279	Proprietary
45	qwen3.6-plus	alibaba	1,460	1,454 / 1,466	16,336	Proprietary
46	gpt-5.5 (codex-harness)	openai	1,458	1,451 / 1,464	13,672	Proprietary
47	gemini-3.5-flash-lite	google	1,449	1,407 / 1,492	228	Proprietary
48	gemini-3.1-pro-preview	google	1,446	1,441 / 1,452	21,573	Proprietary
49	deepseek-v4-pro	deepseek	1,445	1,439 / 1,452	13,178	MIT
50	gpt-5.4-medium (codex-harness)	openai	1,442	1,423 / 1,461	1,318	Proprietary
51	gemini-3-flash	google	1,438	1,429 / 1,447	10,477	Proprietary
52	gemini-3-pro	google	1,438	1,429 / 1,446	13,593	Proprietary
53	mimo-v2.5	xiaomi	1,438	1,431 / 1,444	12,887	MIT
54	kimi-k2.5-thinking	moonshot	1,436	1,431 / 1,441	18,367	Modified MIT
55	glm-5	zai	1,435	1,427 / 1,444	7,068	MIT
56	glm-4.7	zai	1,434	1,422 / 1,447	3,814	MIT
57	mimo-v2-pro	xiaomi	1,434	1,425 / 1,442	6,977	Proprietary
58	deepseek-v4-flash-high-preview	deepseek	1,431	1,424 / 1,438	9,497	MIT
59	gpt-5-medium	openai	1,419	1,403 / 1,435	3,037	Proprietary
60	gpt-5.2	openai	1,418	1,395 / 1,441	1,057	Proprietary
62	inkling	thinky	1,408	1,400 / 1,416	7,088	Apache 2.0
63	kimi-k2.5-instant	moonshot	1,405	1,393 / 1,417	3,108	Modified MIT
64	Inkling Small	thinky	1,402	1,391 / 1,412	3,806	Apache 2.0
65	glm-5v-turbo	zai	1,400	1,386 / 1,414	2,183	Proprietary
66	qwen3.5-397b-a17b	alibaba	1,399	1,394 / 1,405	18,612	Apache 2.0
67	minimax-m2.7	minimax	1,398	1,392 / 1,404	14,198	Modified MIT
68	gpt-5.4-mini-high	openai	1,397	1,390 / 1,404	11,294	Proprietary
69	claude-sonnet-4-5-20250929-high-32k	anthropic	1,392	1,385 / 1,400	12,802	Proprietary
70	gpt-5.1-medium	openai	1,391	1,379 / 1,403	4,758	Proprietary
71	gpt-5.4	openai	1,391	1,376 / 1,405	1,951	Proprietary
72	claude-opus-4-1-20250805	anthropic	1,389	1,378 / 1,400	6,786	Proprietary
73	minimax-m2.1-preview	minimax	1,387	1,377 / 1,397	7,296	MIT
74	claude-sonnet-4-5-20250929	anthropic	1,386	1,378 / 1,393	15,198	Proprietary
75	minimax-m2.5	minimax	1,384	1,375 / 1,392	7,218	Modified MIT
76	gemini-3-flash (thinking-minimal)	google	1,383	1,377 / 1,388	20,948	Proprietary
77	grok-4.20-beta-0309-reasoning	xai	1,374	1,367 / 1,380	14,590	Proprietary
78	solar-pro4	upstage	1,371	1,354 / 1,388	1,405	Proprietary
79	gpt-5.3-codex (codex-harness)	openai	1,369	1,357 / 1,381	3,504	Proprietary
80	gemma-4-31b	google	1,364	1,356 / 1,371	8,965	Apache 2.0
81	gemma-4-26b-a4b	google	1,362	1,344 / 1,379	1,443	Apache 2.0
82	deepseek-v3.2-thinking	deepseek	1,360	1,351 / 1,370	6,656	MIT
83	muse-glimmer	meta	1,359	1,343 / 1,375	1,507	Apache-2.0
84	qwen3.5-122b-a10b	alibaba	1,358	1,350 / 1,365	7,862	Apache 2.0
85	qwen3.5-27b	alibaba	1,357	1,349 / 1,366	7,437	Apache 2.0
86	grok-4.3	xai	1,357	1,350 / 1,363	12,942	Proprietary
87	hunyuan-hy3-preview	tencent	1,356	1,339 / 1,374	1,395	tencent-hunyuan-community
88	laguna-m.1	poolside	1,347	1,338 / 1,357	5,064	Apache 2.0
89	gpt-5.1	openai	1,341	1,332 / 1,349	10,343	Proprietary
90	glm-4.6	zai	1,340	1,329 / 1,351	6,606	MIT
91	gpt-5.2-codex	openai	1,338	1,329 / 1,347	6,424	Proprietary
92	gpt-5.1-codex	openai	1,336	1,325 / 1,348	4,873	Proprietary
93	mimo-v2-flash (non-thinking)	xiaomi	1,330	1,320 / 1,340	5,416	MIT
94	claude-haiku-4-5-20251001	anthropic	1,327	1,322 / 1,332	26,652	Proprietary
95	deepseek-v3.2	deepseek	1,325	1,316 / 1,333	8,988	MIT
96	kimi-k2-thinking-turbo	moonshot	1,323	1,315 / 1,330	12,671	Modified MIT
97	laguna-xs.2	poolside	1,302	1,291 / 1,313	3,935	Apache 2.0
98	minimax-m2	minimax	1,297	1,286 / 1,308	6,538	Apache 2.0
99	mimo-v2-flash (thinking)	xiaomi	1,292	1,276 / 1,309	1,661	MIT
100	qwen3-coder-480b-a35b-instruct	alibaba	1,273	1,265 / 1,281	12,291	Apache 2.0
101	deepseek-v3.2-exp	deepseek	1,272	1,258 / 1,285	3,871	MIT

Par categorie

Webdev

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
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

Webdev react

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5-max	anthropic	1,709	1,699 / 1,720	5,340	Proprietary
2	kimi-k3-max	moonshot	1,692	1,678 / 1,705	3,278	Kimi K3 license
3	claude-opus-5-high	anthropic	1,681	1,671 / 1,690	5,893	Proprietary
4	qwen3.8-max	alibaba	1,678	1,664 / 1,693	2,322	Proprietary
5	grok-4.6-high	xai	1,638	1,617 / 1,659	1,064	Proprietary
6	claude-fable-5	anthropic	1,630	1,620 / 1,639	6,222	Proprietary
7	gpt-5.6-sol-xhigh (codex-harness)	openai	1,625	1,616 / 1,634	6,475	Proprietary
8	glm-5.3-max	zai	1,609	1,590 / 1,628	1,280	MIT
9	qwen3.8-27b	alibaba	1,604	1,588 / 1,621	1,640	Apache 2.0
10	glm-5.2-max	zai	1,594	1,585 / 1,603	6,171	MIT
11	deepseek-v4-pro-high-20260813	deepseek	1,589	1,574 / 1,604	1,867	MIT
12	deepseek-v4-flash-high	deepseek	1,584	1,570 / 1,597	2,446	MIT
13	gemini-3.7-flash-high	google	1,581	1,566 / 1,597	1,785	Proprietary
14	claude-opus-4-8-high	anthropic	1,563	1,555 / 1,571	7,595	Proprietary
15	grok-4.5	xai	1,559	1,549 / 1,568	4,453	Proprietary

Webdev html

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5-max	anthropic	1,685	1,660 / 1,710	840	Proprietary
2	claude-fable-5	anthropic	1,666	1,644 / 1,689	1,001	Proprietary
3	kimi-k3-max	moonshot	1,650	1,617 / 1,682	466	Kimi K3 license
4	claude-opus-5-high	anthropic	1,648	1,626 / 1,670	999	Proprietary
5	grok-4.6-high	xai	1,631	1,581 / 1,682	181	Proprietary
6	qwen3.8-max	alibaba	1,628	1,593 / 1,662	396	Proprietary
7	gemini-3.7-flash-high	google	1,622	1,584 / 1,660	320	Proprietary
8	gpt-5.6-sol-xhigh (codex-harness)	openai	1,618	1,597 / 1,640	1,016	Proprietary
9	qwen3.8-27b	alibaba	1,579	1,541 / 1,618	267	Apache 2.0
10	glm-5.3-max	zai	1,577	1,532 / 1,622	200	MIT
11	grok-4.5	xai	1,577	1,552 / 1,602	683	Proprietary
12	deepseek-v4-pro-high-20260813	deepseek	1,563	1,526 / 1,600	314	MIT
13	claude-opus-4-7	anthropic	1,559	1,544 / 1,575	1,707	Proprietary
14	claude-opus-4-6-high	anthropic	1,559	1,545 / 1,573	2,169	Proprietary
15	claude-opus-4-7-high	anthropic	1,555	1,540 / 1,570	1,862	Proprietary

Image to webdev

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5-max	anthropic	1,670	1,649 / 1,692	922	Proprietary
2	qwen3.8-max	alibaba	1,631	1,612 / 1,651	1,045	Proprietary
3	claude-fable-5	anthropic	1,626	1,613 / 1,639	2,579	Proprietary
4	gpt-5.6-sol-xhigh (codex-harness)	openai	1,581	1,560 / 1,603	806	Proprietary
5	grok-4.5	xai	1,580	1,559 / 1,602	799	Proprietary
6	claude-opus-4-7-thinking	anthropic	1,579	1,568 / 1,589	5,028	Proprietary
7	kimi-k3-max	moonshot	1,570	1,546 / 1,595	634	Kimi K3 license
8	claude-opus-4-7	anthropic	1,565	1,555 / 1,575	5,457	Proprietary
9	muse-spark-1.1	meta	1,544	1,521 / 1,566	771	Proprietary
10	claude-opus-4-6-thinking	anthropic	1,540	1,530 / 1,551	6,020	Proprietary
11	claude-sonnet-5-high	anthropic	1,540	1,528 / 1,553	2,513	Proprietary
12	claude-opus-4-6	anthropic	1,538	1,528 / 1,548	6,097	Proprietary
13	claude-sonnet-4-6	anthropic	1,530	1,520 / 1,540	6,340	Proprietary
14	gemini-3.6-flash	google	1,529	1,500 / 1,558	433	Proprietary
15	gpt-5.5-xhigh (codex-harness)	openai	1,526	1,515 / 1,536	4,968	Proprietary

Voir aussi

Sources et methodologie

Les classements sont agreges depuis des evaluations communautaires ouvertes. Les scores Elo, intervalles de confiance et votes proviennent de LMArena (duels de modeles votes par la communaute, publies en dataset ouvert). Les prix et metadonnees de contexte proviennent de l’API publique OpenRouter. Wikiprompt prend un instantane quotidien et preserve l’historique ; nous ne menons aucune evaluation proprietaire.