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: 2026-10-13 · 140 modeles

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5.5-max	anthropic	1,813	1,798 / 1,828	2,294	Proprietary
2	gpt-6-astra-max	openai	1,786	1,775 / 1,797	5,189	Proprietary
3	claude-sonnet-5.5-xhigh	anthropic	1,774	1,759 / 1,789	2,323	Proprietary
4	gpt-6.1-sol-max	openai	1,755	1,740 / 1,770	2,102	Proprietary
5	claude-fable-5.1-max	anthropic	1,744	1,734 / 1,753	6,663	Proprietary
6	claude-sonnet-5.5-high	anthropic	1,715	1,704 / 1,726	3,984	Proprietary
7	claude-opus-5-max	anthropic	1,691	1,685 / 1,698	17,320	Proprietary
8	gpt-6-sol-max	openai	1,688	1,676 / 1,700	3,407	Proprietary
9	gemini-4-argon-high	google	1,678	1,662 / 1,693	1,771	Proprietary
10	qwen3.8-max-0902	alibaba	1,674	1,666 / 1,681	11,182	Proprietary
11	qwen3.8-max	alibaba	1,672	1,660 / 1,684	3,446	Proprietary
12	claude-opus-5-high	anthropic	1,657	1,651 / 1,662	22,340	Proprietary
13	muse-spark-1.3-max	meta	1,657	1,649 / 1,665	7,886	Proprietary
14	kimi-k3-max	moonshot	1,654	1,648 / 1,661	17,412	Kimi K3 license
15	grok-4.7-xhigh	xai	1,639	1,628 / 1,650	3,936	Proprietary
16	mimo-v2.6-flash	xiaomi	1,637	1,626 / 1,647	4,058	MIT
17	qwen3.8-flash-next	alibaba	1,633	1,624 / 1,641	6,932	qwen-community-1.0
18	hy4-preview	tencent	1,632	1,622 / 1,641	4,792	Apache 2.0
19	mimo-v2.6-pro	xiaomi	1,629	1,618 / 1,640	3,649	MIT
20	muse-spark-1.3 (xHigh)	meta	1,626	1,617 / 1,634	7,123	Proprietary
21	claude-fable-5-high	anthropic	1,625	1,618 / 1,631	14,657	Proprietary
22	glm-5.3-max	zai	1,622	1,614 / 1,630	8,382	MIT
23	deepseek-v4.1-flash-max	deepseek	1,619	1,608 / 1,630	3,542	MIT
24	gpt-5.6-sol-xhigh (codex-harness)	openai	1,618	1,612 / 1,624	16,639	Proprietary
25	grok-4.6-high	xai	1,617	1,609 / 1,625	8,958	Proprietary
26	glm-5.3-flash	zai	1,609	1,602 / 1,616	13,697	MIT
27	glm-5.2-max	zai	1,603	1,597 / 1,609	15,351	MIT
28	qwen3.8-27b	alibaba	1,593	1,586 / 1,600	13,777	Apache 2.0
29	gemini-3.7-flash-high	google	1,592	1,584 / 1,599	10,637	Proprietary
30	claude-haiku-5.5-high	anthropic	1,587	1,567 / 1,607	978	Proprietary
31	gemini-3.8-flash-high	google	1,583	1,576 / 1,591	9,225	Proprietary
32	deepseek-v4-pro-high-20260813	deepseek	1,582	1,573 / 1,591	4,740	MIT
33	deepseek-v4-flash-high	deepseek	1,582	1,572 / 1,591	4,974	MIT
34	gpt-6-luna-max	openai	1,581	1,574 / 1,588	12,332	Proprietary
35	step-5-preview-high	stepfun	1,564	1,552 / 1,575	3,351	Proprietary
36	claude-opus-4-7-high	anthropic	1,557	1,552 / 1,563	17,956	Proprietary
37	claude-opus-4-8-high	anthropic	1,556	1,550 / 1,562	18,534	Proprietary
38	claude-opus-4-7	anthropic	1,555	1,550 / 1,561	18,297	Proprietary
39	grok-4.5	xai	1,553	1,546 / 1,560	11,116	Proprietary
40	claude-opus-4-6-high	anthropic	1,547	1,541 / 1,552	19,434	Proprietary
41	muse-spark-1.1	meta	1,542	1,535 / 1,550	8,002	Proprietary
42	mistral-large-4	mistral	1,541	1,525 / 1,558	1,478	Proprietary
43	claude-sonnet-5-high	anthropic	1,541	1,535 / 1,547	14,574	Proprietary
44	gemini-3.6-flash-high	google	1,538	1,530 / 1,545	8,766	Proprietary
45	claude-opus-4-6	anthropic	1,537	1,532 / 1,543	20,694	Proprietary
46	claude-opus-4-8	anthropic	1,536	1,530 / 1,541	17,435	Proprietary
47	muse-spark-1.2 (xHigh)	meta	1,533	1,519 / 1,546	2,171	Proprietary
48	claude-sonnet-4-6	anthropic	1,522	1,517 / 1,528	22,866	Proprietary
49	gpt-5.6-terra-xhigh (codex-harness)	openai	1,522	1,515 / 1,528	12,367	Proprietary
50	seed-2.1-pro-preview	bytedance	1,519	1,513 / 1,525	13,897	Proprietary
51	gpt-5.6-luna-xhigh (codex-harness)	openai	1,519	1,513 / 1,525	12,556	Proprietary
52	qwen3.7-max-20260517	alibaba	1,515	1,508 / 1,522	8,905	Proprietary
53	gpt-5.5-xhigh (codex-harness)	openai	1,513	1,507 / 1,519	15,698	Proprietary
54	kimi-k2.6	moonshot	1,509	1,502 / 1,516	10,187	Modified MIT
55	hy3	tencent	1,508	1,500 / 1,517	5,660	Apache 2.0
56	glm-5.1	zai	1,508	1,502 / 1,515	10,739	MIT
57	gemini-3.5-flash-high	google	1,499	1,492 / 1,506	9,415	Proprietary
58	claude-opus-4-5-20251101-high-32k	anthropic	1,494	1,486 / 1,502	11,034	Proprietary
59	gemini-3.5-flash-medium	google	1,491	1,484 / 1,498	12,181	Proprietary
60	gpt-5.5-high (codex-harness)	openai	1,487	1,482 / 1,493	18,002	Proprietary
61	qwen3.6-max-preview	alibaba	1,482	1,470 / 1,495	2,708	Proprietary
62	minimax-m3	minimax	1,482	1,476 / 1,487	18,288	MiniMax Community License
63	mimo-v2.5-pro	xiaomi	1,479	1,474 / 1,485	21,036	MIT
64	kimi-k2.7-code	moonshot	1,473	1,464 / 1,483	4,987	Modified MIT
65	claude-opus-4-5-20251101	anthropic	1,469	1,462 / 1,476	13,426	Proprietary
66	gpt-5.4-high (codex-harness)	openai	1,465	1,446 / 1,484	1,350	Proprietary
67	deepseek-v4-pro-high-preview	deepseek	1,464	1,457 / 1,470	13,194	MIT
68	qwen3.6-plus	alibaba	1,461	1,456 / 1,467	18,621	Proprietary
69	gpt-5.5 (codex-harness)	openai	1,456	1,450 / 1,462	15,911	Proprietary
70	deepseek-v4-pro	deepseek	1,447	1,440 / 1,453	14,019	MIT
71	gemini-3.1-pro-preview	google	1,447	1,442 / 1,452	24,249	Proprietary
72	gpt-5.4-medium (codex-harness)	openai	1,444	1,426 / 1,463	1,376	Proprietary
73	gemini-3.5-flash-lite	google	1,440	1,399 / 1,480	242	Proprietary
74	gemini-3-pro	google	1,440	1,431 / 1,448	14,090	Proprietary
75	gemini-3-flash	google	1,439	1,431 / 1,448	10,894	Proprietary
76	mimo-v2.5	xiaomi	1,438	1,432 / 1,444	14,947	MIT
77	kimi-k2.5-thinking	moonshot	1,436	1,431 / 1,442	20,127	Modified MIT
78	glm-4.7	zai	1,435	1,423 / 1,447	4,007	MIT
79	glm-5	zai	1,434	1,426 / 1,443	7,506	MIT
80	mimo-v2-pro	xiaomi	1,433	1,425 / 1,441	7,244	Proprietary
81	deepseek-v4-flash-high-preview	deepseek	1,431	1,424 / 1,438	10,144	MIT
82	gpt-5-medium	openai	1,418	1,402 / 1,433	3,092	Proprietary
83	gpt-5.2	openai	1,416	1,394 / 1,438	1,082	Proprietary
84	inkling	thinky	1,413	1,407 / 1,419	14,358	Apache 2.0
85	Inkling Small	thinky	1,409	1,400 / 1,418	5,368	Apache 2.0
87	kimi-k2.5-instant	moonshot	1,404	1,392 / 1,416	3,269	Modified MIT
88	glm-5v-turbo	zai	1,401	1,388 / 1,414	2,411	Proprietary
89	gpt-5.4	openai	1,400	1,390 / 1,411	3,734	Proprietary
90	qwen3.5-397b-a17b	alibaba	1,400	1,395 / 1,405	21,189	Apache 2.0
91	minimax-m2.7	minimax	1,398	1,392 / 1,404	16,011	Modified MIT
92	gpt-5.4-mini-high	openai	1,397	1,391 / 1,404	11,976	Proprietary
93	gpt-5.1-medium	openai	1,395	1,384 / 1,407	4,912	Proprietary
94	claude-sonnet-4-5-20250929-high-32k	anthropic	1,393	1,386 / 1,401	13,256	Proprietary
95	claude-opus-4-1-20250805	anthropic	1,390	1,379 / 1,401	6,926	Proprietary
96	minimax-m2.5	minimax	1,387	1,378 / 1,395	7,635	Modified MIT
97	gemini-3-flash (thinking-minimal)	google	1,385	1,379 / 1,390	22,176	Proprietary
98	claude-sonnet-4-5-20250929	anthropic	1,385	1,377 / 1,392	15,723	Proprietary
99	minimax-m2.1-preview	minimax	1,384	1,375 / 1,394	7,645	MIT
100	grok-4.20-beta-0309-reasoning	xai	1,375	1,369 / 1,381	15,474	Proprietary
101	gpt-5.3-codex (codex-harness)	openai	1,371	1,360 / 1,383	3,656	Proprietary

Par categorie

Overall

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5.5-max	anthropic	1,813	1,798 / 1,828	2,294	Proprietary
2	gpt-6-astra-max	openai	1,786	1,775 / 1,797	5,189	Proprietary
3	claude-sonnet-5.5-xhigh	anthropic	1,774	1,759 / 1,789	2,323	Proprietary
4	gpt-6.1-sol-max	openai	1,755	1,740 / 1,770	2,102	Proprietary
5	claude-fable-5.1-max	anthropic	1,744	1,734 / 1,753	6,663	Proprietary
6	claude-sonnet-5.5-high	anthropic	1,715	1,704 / 1,726	3,984	Proprietary
7	claude-opus-5-max	anthropic	1,691	1,685 / 1,698	17,320	Proprietary
8	gpt-6-sol-max	openai	1,688	1,676 / 1,700	3,407	Proprietary
9	gemini-4-argon-high	google	1,678	1,662 / 1,693	1,771	Proprietary
10	qwen3.8-max-0902	alibaba	1,674	1,666 / 1,681	11,182	Proprietary
11	qwen3.8-max	alibaba	1,672	1,660 / 1,684	3,446	Proprietary
12	claude-opus-5-high	anthropic	1,657	1,651 / 1,662	22,340	Proprietary
13	muse-spark-1.3-max	meta	1,657	1,649 / 1,665	7,886	Proprietary
14	kimi-k3-max	moonshot	1,654	1,648 / 1,661	17,412	Kimi K3 license
15	grok-4.7-xhigh	xai	1,639	1,628 / 1,650	3,936	Proprietary

Webdev react

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5.5-max	anthropic	1,863	1,843 / 1,882	1,576	Proprietary
2	claude-sonnet-5.5-xhigh	anthropic	1,824	1,805 / 1,843	1,469	Proprietary
3	gpt-6-astra-max	openai	1,811	1,797 / 1,825	3,044	Proprietary
4	claude-fable-5.1-max	anthropic	1,793	1,781 / 1,805	4,485	Proprietary
5	gpt-6.1-sol-max	openai	1,758	1,739 / 1,777	1,306	Proprietary
6	claude-sonnet-5.5-high	anthropic	1,749	1,735 / 1,762	2,574	Proprietary
7	claude-opus-5-max	anthropic	1,714	1,707 / 1,722	11,288	Proprietary
8	gpt-6-sol-max	openai	1,693	1,678 / 1,708	1,955	Proprietary
9	qwen3.8-max-0902	alibaba	1,691	1,682 / 1,700	7,027	Proprietary
10	gemini-4-argon-high	google	1,690	1,670 / 1,710	1,089	Proprietary
11	qwen3.8-max	alibaba	1,682	1,668 / 1,697	2,506	Proprietary
12	claude-opus-5-high	anthropic	1,677	1,671 / 1,684	14,705	Proprietary
13	muse-spark-1.3-max	meta	1,669	1,660 / 1,679	5,088	Proprietary
14	kimi-k3-max	moonshot	1,669	1,662 / 1,676	11,630	Kimi K3 license
15	grok-4.7-xhigh	xai	1,661	1,648 / 1,675	2,416	Proprietary

Webdev html

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	gpt-6.1-sol-max	openai	1,797	1,760 / 1,834	392	Proprietary
2	gpt-6-astra-max	openai	1,784	1,761 / 1,808	1,063	Proprietary
3	claude-opus-5.5-max	anthropic	1,761	1,694 / 1,828	111	Proprietary
4	claude-sonnet-5.5-xhigh	anthropic	1,739	1,699 / 1,779	364	Proprietary
5	claude-sonnet-5.5-high	anthropic	1,709	1,682 / 1,736	634	Proprietary
6	gpt-6-sol-max	openai	1,686	1,660 / 1,712	688	Proprietary
7	claude-fable-5.1-max	anthropic	1,686	1,661 / 1,710	797	Proprietary
8	claude-opus-5-max	anthropic	1,681	1,666 / 1,696	2,123	Proprietary
9	muse-spark-1.3-max	meta	1,657	1,637 / 1,677	1,112	Proprietary
10	claude-opus-5-high	anthropic	1,653	1,640 / 1,665	3,091	Proprietary
11	claude-fable-5-high	anthropic	1,651	1,636 / 1,666	2,000	Proprietary
12	qwen3.8-max-0902	alibaba	1,649	1,633 / 1,665	1,929	Proprietary
13	kimi-k3-max	moonshot	1,646	1,631 / 1,660	2,373	Kimi K3 license
14	mimo-v2.6-flash	xiaomi	1,643	1,617 / 1,668	630	MIT
15	gemini-4-argon-high	google	1,642	1,594 / 1,690	188	Proprietary

Image to webdev

Rang	Modele	Organisation	Score Elo	IC 95%	Votes	Licence
1	claude-opus-5.5-max	anthropic	1,749	1,718 / 1,779	493	Proprietary
2	claude-sonnet-5.5-xhigh	anthropic	1,740	1,720 / 1,760	1,074	Proprietary
3	gpt-6-astra-max	openai	1,731	1,718 / 1,745	2,739	Proprietary
4	claude-fable-5.1-max	anthropic	1,720	1,706 / 1,733	2,470	Proprietary
5	gpt-6.1-sol-max	openai	1,703	1,686 / 1,721	1,430	Proprietary
6	gpt-6-sol-max	openai	1,661	1,648 / 1,674	2,426	Proprietary
7	claude-opus-5-max	anthropic	1,661	1,651 / 1,671	4,250	Proprietary
8	muse-spark-1.3-max	meta	1,642	1,632 / 1,652	4,688	Proprietary
9	qwen3.8-max-0902	alibaba	1,638	1,620 / 1,656	1,164	Proprietary
10	claude-fable-5-high	anthropic	1,622	1,613 / 1,632	5,457	Proprietary
11	qwen3.8-max	alibaba	1,614	1,603 / 1,624	3,971	Proprietary
12	deepseek-v4.1-flash-max	deepseek	1,609	1,587 / 1,631	766	MIT
13	gpt-5.6-sol-xhigh (codex-harness)	openai	1,608	1,598 / 1,618	4,478	Proprietary
14	gemini-3.7-flash-high	google	1,603	1,590 / 1,617	2,144	Proprietary
15	grok-4.6-high	xai	1,601	1,589 / 1,613	2,826	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.