LLM बेंचमार्क

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

Wikiprompt से, प्रॉम्प्ट का मुक्त विश्वकोश

भाषा मॉडल और जनरेटिव AI की लाइव रैंकिंग, सामुदायिक खुली मूल्यांकन से दैनिक रूप से एकत्रित। प्रत्येक तालिका अपने स्रोत का हवाला देती है, और चूंकि Wikiprompt दैनिक स्नैपशॉट रखता है, रैंकिंग में बदलाव दर्ज किए जाते हैं।

अंतिम अपडेट: 2026-09-22 · यह लाइव रैंकिंग है; दिनांकित स्नैपशॉट प्रत्येक पिछली रैंकिंग को संरक्षित करते हैं। इतिहास →

इंटरैक्टिव एक्सप्लोरर

एरिना, संगठन या लाइसेंस द्वारा फ़िल्टर करें, मॉडल खोजें, तालिका क्रमबद्ध करें और लागत बनाम प्रदर्शन ग्राफ़ पढ़ें। नीचे दी गई तालिकाएँ उद्धरण योग्य संदर्भ बनी रहती हैं।

आप देख रहे हैं

LMArena · टेक्स्ट एरिना

LMArena पर मतदान किए गए आमने-सामने की लड़ाइयों का सामुदायिक Elo।

मूल्य और संदर्भ: OpenRouter (नाम से मिलान)

टेक्स्ट एरिना

मॉडल को पिन करने और केवल उनकी तुलना करने के लिए पंक्तियों या ग्राफ़ बिंदुओं पर क्लिक करें।

लागत बनाम प्रदर्शन

आउटपुट मूल्य USD में प्रति 1M टोकन (लॉग स्केल, OpenRouter से) बनाम सामुदायिक Elo (LMArena)। ऊपर बाईं ओर = सर्वोत्तम मूल्य।

सबसे आकर्षक चतुर्थांशपेरेटो रेखाग्राफ़ में सभी दिखाएंपैमाना:

एक क्यूरेटेड सबसेट दिखा रहे हैं (संगठन के अनुसार शीर्ष)। मॉडल चुनें या 'सभी दिखाएं' चिह्नित करें।

समय के साथ Elo (शीर्ष टेक्स्ट मॉडल)

स्थान ▲	मॉडल	संगठन	Elo स्कोर	वोट	इनपुट $/1M	आउटपुट $/1M	संदर्भ
2	claude-opus-5-max	anthropic	1,505	20,706	$5	$25	1,000,000
3	claude-opus-5-high	anthropic	1,505	42,617	$5	$25	1,000,000
4	claude-opus-4-6-high	anthropic	1,503	71,993	$5	$25	1,000,000
5	claude-opus-4-6	anthropic	1,498	75,878	$5	$25	1,000,000
7	claude-fable-5	anthropic	1,493	30,057	$10	$50	1,000,000
9	claude-opus-4-7-high	anthropic	1,490	60,002	$5	$25	1,000,000
12	claude-opus-4-7	anthropic	1,483	61,128	$5	$25	1,000,000
13	gemini-3.5-flash-high	google	1,482	38,257	$1.5	$9	1,048,576
15	muse-spark-1.1	meta	1,480	27,615	$1.25	$4.25	1,048,576
16	gemini-3.1-pro-preview	google	1,480	106,951	$2	$12	1,048,576
17	gemini-3-pro	google	1,479	40,654	$2	$12	131,072
18	gemini-3.6-flash-high	google	1,476	26,445	$0.75	$3.75	1,048,576
19	gemini-3.5-flash-medium	google	1,476	36,627	$1.5	$9	1,048,576
23	kimi-k3-max	moonshot	1,472	20,987	$3	$15	1,048,576
25	qwen3.5-max-preview	alibaba	1,471	21,476
26	gpt-5.5-high	openai	1,471	64,924	$5	$30	1,050,000
28	ernie-5.1	baidu	1,468	37,058
29	glm-5.2-max	zai	1,467	36,798	$0.65	$2.04	1,048,576
32	mimo-v2.5-pro	xiaomi	1,465	60,919	$0.44	$0.87	1,050,000
42	grok-4.20-beta-0309-reasoning	xai	1,451	62,168	$1.25	$2.5	2,000,000
43	deepseek-v4-pro	deepseek	1,451	54,130	$0.94	$1.88	1,048,576
48	dola-seed-2.0-pro	bytedance	1,448	74,159
67	inkling	thinky	1,440	25,922	$1	$4.05	1,048,576
82	minimax-m3	minimax	1,433	48,540	$0.3	$1.2	1,048,576
91	mistral-large-3	mistral	1,427	69,028	$0.25	$0.75	262,144
92	longcat-flash-chat-2602-exp	meituan	1,426	27,962
120	amazon-nova-experimental-chat-11-10	amazon	1,416	25,086
140	step-3.5-flash	stepfun	1,404	57,137	$0.1	$0.3	262,144

मूल्य सामान्यीकृत नाम द्वारा OpenRouter की निकटतम सूची से मिलाए जाते हैं; प्रयास भिन्नताएँ आधार मॉडल का मूल्य साझा करती हैं।

निष्कर्ष

• टेक्स्ट एरिना का वर्तमान नेता: claude-opus-5-max (anthropic, Elo 1505)
• सर्वोत्तम मूल्य (प्रति डॉलर Elo, $2/1M आउटपुट से कम): mimo-v2.5-pro (Elo 1465, $0.87/1M)
• सबसे मजबूत खुला मॉडल: kimi-k3-max (Kimi K3 license, #23)
• कोडिंग में नेता (Aider पास दर): gpt-5 (high) (88%)

सामग्री

टेक्स्ट एरिना
वेब विकास एरिना
विज़न एरिना
टेक्स्ट-से-छवि एरिना
छवि संपादन एरिना
टेक्स्ट-से-वीडियो एरिना
वीडियो संपादन एरिना
खोज एरिना
एजेंट एरिना
दस्तावेज़ एरिना
मूल्य और संदर्भ विंडो
हाल के बदलाव
स्रोत और पद्धति

टेक्स्ट एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्रोत और पद्धति: LMArena · LMArena पर मतदान किए गए आमने-सामने की लड़ाइयों का सामुदायिक Elo।

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
2	claude-opus-5-max	anthropic	1,505	1,500 / 1,510	20,706	Proprietary
3	claude-opus-5-high	anthropic	1,505	1,501 / 1,509	42,617	Proprietary
4	claude-opus-4-6-high	anthropic	1,503	1,499 / 1,506	71,993	Proprietary
5	claude-opus-4-6	anthropic	1,498	1,494 / 1,501	75,878	Proprietary
7	claude-fable-5	anthropic	1,493	1,488 / 1,497	30,057	Proprietary
9	claude-opus-4-7-high	anthropic	1,490	1,486 / 1,494	60,002	Proprietary
12	claude-opus-4-7	anthropic	1,483	1,479 / 1,487	61,128	Proprietary
13	gemini-3.5-flash-high	google	1,482	1,478 / 1,486	38,257	Proprietary
15	muse-spark-1.1	meta	1,480	1,475 / 1,485	27,615	Proprietary
16	gemini-3.1-pro-preview	google	1,480	1,477 / 1,483	106,951	Proprietary
17	gemini-3-pro	google	1,479	1,476 / 1,483	40,654	Proprietary
18	gemini-3.6-flash-high	google	1,476	1,471 / 1,481	26,445	Proprietary
19	gemini-3.5-flash-medium	google	1,476	1,471 / 1,480	36,627	Proprietary
23	kimi-k3-max	moonshot	1,472	1,467 / 1,477	20,987	Kimi K3 license
25	qwen3.5-max-preview	alibaba	1,471	1,466 / 1,476	21,476	Proprietary
26	gpt-5.5-high	openai	1,471	1,467 / 1,475	64,924	Proprietary
27	gpt-5.4-high	openai	1,470	1,466 / 1,473	60,537	Proprietary
28	ernie-5.1	baidu	1,468	1,464 / 1,473	37,058	Proprietary
29	glm-5.2-max	zai	1,467	1,462 / 1,472	36,798	MIT
30	gemini-3-flash	google	1,467	1,462 / 1,471	30,225	Proprietary
31	gpt-5.5	openai	1,466	1,462 / 1,469	66,317	Proprietary
32	mimo-v2.5-pro	xiaomi	1,465	1,461 / 1,469	60,919	MIT
33	glm-5.1	zai	1,462	1,459 / 1,466	48,901	MIT
34	claude-opus-4-8-high	anthropic	1,461	1,457 / 1,465	52,535	Proprietary
35	claude-sonnet-4-6	anthropic	1,458	1,455 / 1,462	66,208	Proprietary

वेब विकास एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	gpt-6-astra-max	openai	1,800	1,784 / 1,817	2,281	Proprietary
2	claude-fable-5.1-max	anthropic	1,758	1,744 / 1,772	3,036	Proprietary
3	claude-opus-5-max	anthropic	1,687	1,680 / 1,694	12,087	Proprietary
4	qwen3.8-max-0902	alibaba	1,681	1,666 / 1,695	2,262	Proprietary
5	kimi-k3-max	moonshot	1,674	1,663 / 1,685	4,547	Kimi K3 license
6	qwen3.8-max	alibaba	1,671	1,658 / 1,683	3,221	Proprietary
7	claude-opus-5-high	anthropic	1,660	1,653 / 1,667	12,566	Proprietary
8	muse-spark-1.3-max	meta	1,652	1,640 / 1,664	2,972	Proprietary
9	qwen3.8-flash-next	alibaba	1,635	1,623 / 1,648	2,779	qwen-community-1.0
10	claude-fable-5	anthropic	1,628	1,621 / 1,635	10,081	Proprietary
11	hy4-preview	tencent	1,624	1,611 / 1,638	2,321	Apache 2.0
12	muse-spark-1.3 (xHigh)	meta	1,623	1,609 / 1,637	2,123	Proprietary
13	grok-4.6-high	xai	1,618	1,607 / 1,628	4,282	Proprietary
14	gpt-5.6-sol-xhigh (codex-harness)	openai	1,617	1,610 / 1,624	11,916	Proprietary
15	glm-5.3-max	zai	1,614	1,604 / 1,625	3,725	MIT
16	deepseek-v4.1-flash-max	deepseek	1,614	1,597 / 1,631	1,361	MIT
17	glm-5.3-flash	zai	1,607	1,595 / 1,619	2,925	MIT
18	qwen3.8-27b	alibaba	1,593	1,584 / 1,603	4,913	Apache 2.0
19	glm-5.2-max	zai	1,592	1,585 / 1,599	10,516	MIT
20	gemini-3.7-flash-high	google	1,587	1,575 / 1,599	3,007	Proprietary
21	deepseek-v4-pro-high-20260813	deepseek	1,581	1,571 / 1,590	4,258	MIT
22	deepseek-v4-flash-high	deepseek	1,580	1,571 / 1,590	4,723	MIT
23	gemini-3.8-flash-high	google	1,568	1,555 / 1,580	2,732	Proprietary
24	claude-opus-4-8-high	anthropic	1,559	1,552 / 1,565	13,787	Proprietary
25	claude-opus-4-7	anthropic	1,557	1,551 / 1,563	15,914	Proprietary

विज़न एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	claude-fable-5	anthropic	1,326	1,318 / 1,334	11,304	Proprietary
2	claude-fable-5.1-max	anthropic	1,322	1,310 / 1,335	2,701	Proprietary
3	claude-opus-5-high	anthropic	1,321	1,314 / 1,329	11,599	Proprietary
4	claude-opus-4-7	anthropic	1,318	1,311 / 1,324	21,450	Proprietary
5	claude-opus-4-7-high	anthropic	1,316	1,309 / 1,323	21,092	Proprietary
6	qwen3.8-max	alibaba	1,315	1,307 / 1,323	8,665	Proprietary
7	claude-opus-4-6-high	anthropic	1,315	1,309 / 1,322	20,835	Proprietary
8	muse-spark-1.3-max	meta	1,315	1,300 / 1,329	1,804	Proprietary
9	claude-opus-4-6	anthropic	1,312	1,305 / 1,318	25,140	Proprietary
10	gemini-3.5-flash-high	google	1,310	1,302 / 1,318	9,579	Proprietary
11	gemini-3.5-flash-medium	google	1,307	1,299 / 1,315	9,618	Proprietary
12	muse-spark	meta	1,306	1,297 / 1,315	5,572	Proprietary
13	gemini-3-pro	google	1,304	1,297 / 1,312	12,995	Proprietary
14	muse-spark-1.2 (xHigh)	meta	1,304	1,289 / 1,319	1,841	Proprietary
15	gpt-5.4-high	openai	1,302	1,296 / 1,308	25,357	Proprietary
16	gemini-3.6-flash-high	google	1,300	1,290 / 1,309	5,159	Proprietary
17	glm-5.3-flash	zai	1,299	1,287 / 1,310	3,110	MIT
18	gpt-5.5	openai	1,298	1,291 / 1,304	23,423	Proprietary
19	gemini-3.1-pro-preview	google	1,296	1,290 / 1,301	40,691	Proprietary
20	gpt-5.5-high	openai	1,294	1,288 / 1,301	21,960	Proprietary
21	muse-spark-1.1	meta	1,294	1,286 / 1,302	8,447	Proprietary
22	gpt-5.4	openai	1,293	1,286 / 1,299	21,188	Proprietary
23	claude-opus-4-8-high	anthropic	1,292	1,285 / 1,299	15,274	Proprietary
24	grok-4.5	xai	1,289	1,280 / 1,297	8,355	Proprietary
25	claude-opus-4-8	anthropic	1,288	1,281 / 1,295	15,801	Proprietary

टेक्स्ट-से-छवि एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	gpt-image-2.5-sunburst	openai	1,421	1,408 / 1,434	3,149	Proprietary
2	gpt-image-2.5-flare	openai	1,399	1,386 / 1,412	2,856	Proprietary
3	gpt-image-2 (medium)	openai	1,381	1,377 / 1,386	78,731	Proprietary
4	mai-image-2.6	microsoft-ai	1,331	1,324 / 1,338	11,213	Proprietary
5	grok-imagine-image-2.0 (low)	xai	1,315	1,303 / 1,327	2,681	Proprietary
6	reve-2.1	reve	1,301	1,293 / 1,309	7,573	Proprietary
7	muse-image	meta	1,277	1,271 / 1,283	26,045	Proprietary
8	reve-2.0	reve	1,270	1,264 / 1,277	14,632	Proprietary
9	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,261	1,256 / 1,265	41,957	Proprietary
10	seedream-5.0-pro	bytedance	1,257	1,253 / 1,261	62,443	Proprietary
11	qwen-image-3.0-pro	alibaba	1,254	1,248 / 1,261	10,920	Proprietary
12	mai-image-2.5	microsoft-ai	1,254	1,250 / 1,258	57,250	Proprietary
13	gemini-3.1-flash-lite-image (nano-banana-2-lite)	google	1,250	1,244 / 1,257	16,371	Proprietary
14	gemini-3-pro-image-2k (nano-banana-pro)	google	1,246	1,243 / 1,249	152,220	Proprietary
15	gpt-image-1.5-high-fidelity	openai	1,239	1,236 / 1,242	151,702	Proprietary
16	gemini-3-pro-image-preview (nano-banana-pro)	google	1,232	1,227 / 1,237	82,737	Proprietary
17	ideogram-4.0-quality	ideogram	1,204	1,200 / 1,209	42,169	Ideogram Open Model
18	qwen-image-2.0-pro-2026-06-22	alibaba	1,191	1,185 / 1,197	12,005	Proprietary
19	uni-1.1-max	luma-ai	1,188	1,182 / 1,194	13,469	Proprietary
20	mai-image-2	microsoft-ai	1,183	1,178 / 1,187	49,198	Proprietary
21	uni-1.1	luma-ai	1,181	1,177 / 1,186	33,836	Proprietary
22	grok-imagine-image	xai	1,171	1,168 / 1,173	236,623	Proprietary
23	recraft-v4.1-utility-pro	recraft	1,169	1,158 / 1,180	2,516	Proprietary
24	Cosmos3-Super-Text2Image (Agentic)	nvidia	1,167	1,159 / 1,175	7,424	OpenMDW-1.1
25	flux-2-max	bfl	1,162	1,158 / 1,166	117,339	Proprietary

छवि संपादन एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	gpt-image-2.5-sunburst	openai	1,520	1,511 / 1,530	6,704	Proprietary
2	gpt-image-2.5-flare	openai	1,491	1,481 / 1,500	5,676	Proprietary
3	gpt-image-2 (medium)	openai	1,461	1,458 / 1,465	235,928	Proprietary
4	grok-imagine-image-2.0 (low)	xai	1,439	1,430 / 1,447	5,941	Proprietary
5	mai-image-2.6	microsoft-ai	1,434	1,426 / 1,442	9,481	Proprietary
6	muse-image	meta	1,403	1,398 / 1,408	83,408	Proprietary
7	mai-image-2.5	microsoft-ai	1,400	1,396 / 1,404	174,744	Proprietary
8	seedream-5.0-pro	bytedance	1,394	1,391 / 1,398	179,966	Proprietary
9	gemini-3-pro-image-2k (nano-banana-pro)	google	1,390	1,387 / 1,393	556,580	Proprietary
10	grok-imagine-image-quality (20260519)	xai	1,390	1,384 / 1,395	35,594	Proprietary
11	chatgpt-image-latest-high-fidelity (20251216)	openai	1,389	1,387 / 1,392	543,587	Proprietary
12	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,387	1,384 / 1,391	157,693	Proprietary
13	gemini-3-pro-image-preview (nano-banana-pro)	google	1,385	1,383 / 1,388	518,495	Proprietary
14	reve-2.1	reve	1,375	1,369 / 1,382	19,125	Proprietary
15	gpt-image-1.5-high-fidelity	openai	1,370	1,367 / 1,373	566,510	Proprietary
16	reve-2.0	reve	1,358	1,352 / 1,365	17,505	Proprietary
17	uni-1.1-max	luma-ai	1,333	1,328 / 1,339	40,916	Proprietary
18	grok-imagine-image	xai	1,330	1,327 / 1,332	624,951	Proprietary
19	gemini-3.1-flash-lite-image (nano-banana-2-lite)	google	1,314	1,309 / 1,319	59,280	Proprietary
20	uni-1.1	luma-ai	1,314	1,310 / 1,317	132,966	Proprietary
21	qwen-image-2.0-pro-2026-06-22	alibaba	1,304	1,299 / 1,308	50,820	Proprietary
22	hunyuan-image-3.0-instruct	tencent	1,302	1,299 / 1,306	307,730	tencent-hunyuan-community
23	wan2.7-image-pro	alibaba	1,302	1,298 / 1,306	41,535	Proprietary
24	seedream-4.5	bytedance	1,302	1,299 / 1,304	1,100,289	Proprietary
25	wan2.7-image	alibaba	1,301	1,297 / 1,305	42,373	Proprietary

टेक्स्ट-से-वीडियो एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	gemini-omni-1.1-flash	google	1,515	1,499 / 1,530	1,777	Proprietary
2	gemini-omni-flash	google	1,511	1,502 / 1,521	21,934	Proprietary
3	wan3.0	alibaba	1,494	1,475 / 1,514	1,167	Proprietary
4	flux-3-video	bfl	1,494	1,476 / 1,511	1,290	Proprietary
5	grok-imagine-video-1.5-agent	xai	1,491	1,473 / 1,510	1,195	Proprietary
6	dreamina-seedance-2.5-720p	bytedance	1,482	1,470 / 1,494	4,066	Proprietary
7	dreamina-seedance-2.0-720p	bytedance	1,479	1,471 / 1,487	52,864	Proprietary
8	minimax-h3	minimax	1,462	1,452 / 1,472	7,648	minimax-h3-community-license-agreement
9	muse-video	meta	1,456	1,442 / 1,471	2,178	Proprietary
10	happyhorse-1.0	aorizon	1,427	1,415 / 1,440	22,116	Proprietary
11	sora-2-pro	openai	1,367	1,360 / 1,373	50,415	Proprietary
12	veo-3.1-audio	google	1,364	1,350 / 1,379	13,703	Proprietary
13	veo-3.1-audio-1080p	google	1,363	1,352 / 1,373	24,979	Proprietary
14	veo-3.1-fast-audio	google	1,362	1,351 / 1,372	39,373	Proprietary
15	veo-3.1-fast-audio-1080p	google	1,358	1,348 / 1,368	25,770	Proprietary
16	veo-3-fast-audio	google	1,348	1,336 / 1,359	25,169	Proprietary
17	grok-imagine-video-720p	xai	1,343	1,336 / 1,350	159,930	Proprietary
18	sora-2	openai	1,342	1,336 / 1,348	67,388	Proprietary
19	wan2.7-t2v	wan	1,341	1,333 / 1,349	23,025	Proprietary
20	veo-3-audio	google	1,340	1,327 / 1,352	18,941	Proprietary
21	wan2.6-t2v	alibaba	1,328	1,320 / 1,335	49,348	Proprietary
22	seedance-v1.5-pro	bytedance	1,256	1,249 / 1,263	75,891	Proprietary
23	veo-3	google	1,253	1,242 / 1,265	14,951	Proprietary
24	veo-3-fast	google	1,248	1,236 / 1,260	15,225	Proprietary
25	wan2.5-t2v-preview	alibaba	1,246	1,238 / 1,255	32,461	Proprietary

वीडियो संपादन एरिना10 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	wan3.0	alibaba	1,414	1,388 / 1,440	463	Proprietary
2	dreamina-seedance-2.5-720p	bytedance	1,410	1,383 / 1,436	429	Proprietary
3	minimax-h3	minimax	1,392	1,374 / 1,411	962	minimax-h3-community-license-agreement
4	gemini-omni-flash	google	1,367	1,352 / 1,381	2,109	Proprietary
5	dreamina-seedance-2.0-720p	bytedance	1,365	1,350 / 1,379	3,852	Proprietary
6	happyhorse-1.0	aorizon	1,307	1,293 / 1,320	3,116	Proprietary
7	grok-imagine-video	xai	1,258	1,247 / 1,268	13,724	Proprietary
8	kling-o3-pro	kling	1,255	1,244 / 1,267	7,540	Proprietary
9	kling-o1-pro	kling	1,197	1,187 / 1,208	10,542	Proprietary
10	runway-gen4-aleph	runway	1,182	1,174 / 1,191	9,818	Proprietary

खोज एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	gpt-5.6-sol-xhigh	openai	1,257	1,250 / 1,265	29,663	Proprietary
2	claude-opus-4-6-search	anthropic	1,253	1,248 / 1,258	134,699	Proprietary
3	gpt-5.5-search	openai	1,242	1,237 / 1,247	89,873	Proprietary
4	claude-opus-4-7	anthropic	1,233	1,228 / 1,239	91,394	Proprietary
5	claude-fable-5	anthropic	1,230	1,222 / 1,238	41,795	Proprietary
6	ernie-5.1	baidu	1,227	1,217 / 1,237	3,788	Proprietary
7	claude-sonnet-4-6-search	anthropic	1,221	1,216 / 1,226	134,905	Proprietary
8	grok-4.5	xai	1,213	1,206 / 1,220	31,505	Proprietary
9	gemini-3.1-pro-grounding	google	1,210	1,205 / 1,216	113,282	Proprietary
10	gemini-3-pro-grounding	google	1,207	1,202 / 1,213	37,024	Proprietary
11	gpt-5.2-search	openai	1,207	1,201 / 1,213	52,712	Proprietary
12	claude-opus-4-8	anthropic	1,204	1,198 / 1,211	70,998	Proprietary
13	grok-4.20-multi-agent-beta-0309	xai	1,204	1,199 / 1,209	109,553	Proprietary
14	gpt-5.1-search	openai	1,199	1,194 / 1,205	59,909	Proprietary
15	gemini-3-flash-grounding	google	1,198	1,193 / 1,203	149,334	Proprietary
16	gpt-5.4-search	openai	1,197	1,192 / 1,203	110,116	Proprietary
17	claude-sonnet-5-search	anthropic	1,194	1,187 / 1,201	40,230	Proprietary
18	grok-4.20-beta1	xai	1,189	1,183 / 1,195	53,921	Proprietary
19	claude-opus-4-5-search	anthropic	1,180	1,174 / 1,185	61,573	Proprietary
20	gpt-5.2-search-non-reasoning	openai	1,172	1,167 / 1,178	75,658	Proprietary
21	grok-4-1-fast-search	xai	1,171	1,166 / 1,176	81,507	Proprietary
22	grok-4-fast-search	xai	1,171	1,166 / 1,175	41,794	Proprietary
23	grok-4.3	xai	1,165	1,160 / 1,170	91,483	Proprietary
24	claude-sonnet-4-5-search	anthropic	1,158	1,153 / 1,163	127,378	Proprietary
25	claude-opus-4-1-search	anthropic	1,148	1,143 / 1,153	76,933	Proprietary

एजेंट एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	लाइसेंस
1	Claude Fable 5.1 (Max)	anthropic	Proprietary
2	GPT 6 Astra (Max)	openai	Proprietary
3	Claude Opus 5 (High)	anthropic	Proprietary
4	Claude Opus 5 (Max)	anthropic	Proprietary
5	Claude Fable 5 (High)	anthropic	Proprietary
6	Claude Opus 4.8 (High)	anthropic	Proprietary
7	GPT 5.6 Sol (xHigh)	openai	Proprietary
8	Kimi K3 (Max)	moonshot	Kimi K3 license
9	Claude Sonnet 5 (High)	anthropic	Proprietary
10	GPT 5.5 (xHigh)	openai	Proprietary
11	Hy4 preview	tencent	Apache 2.0
12	Deepseek V4.1 Flash (Max)	deepseek	MIT
13	Gemini 3.8 Flash (High)	google	Proprietary
14	GLM 5.2 (Max)	zai	MIT
15	Muse Spark 1.3 (Max)	meta	Proprietary
16	DeepSeek V4 Pro (High) (0813)	deepseek	MIT
17	Qwen3.8 Max	alibaba	Proprietary
18	GLM 5.3 (Max)	zai	MIT
19	Grok 4.5	xai	Proprietary
20	GPT 5.5	openai	Proprietary
21	Grok 4.6 (xHigh)	xai	Proprietary
22	Deepseek V4 Flash (High) (20260731)	deepseek	MIT
23	GPT 5.6 Terra (xHigh)	openai	Proprietary
24	GPT 5.4 (High)	openai	Proprietary
25	GLM 5.3 Flash	zai	MIT

दस्तावेज़ एरिना25 मॉडलपूर्ण लीडरबोर्ड →

स्थान	मॉडल	संगठन	Elo स्कोर	95% CI	वोट	लाइसेंस
1	claude-opus-5-high	anthropic	1,516	1,509 / 1,523	8,794	Proprietary
2	claude-fable-5.1-max	anthropic	1,513	1,497 / 1,528	1,403	Proprietary
3	claude-opus-4-6-high	anthropic	1,507	1,501 / 1,514	27,929	Proprietary
4	claude-opus-4-6	anthropic	1,507	1,501 / 1,513	41,260	Proprietary
5	claude-fable-5	anthropic	1,496	1,488 / 1,504	8,497	Proprietary
6	claude-opus-4-7	anthropic	1,495	1,489 / 1,501	22,192	Proprietary
7	claude-opus-4-7-high	anthropic	1,495	1,488 / 1,501	21,957	Proprietary
8	gpt-5.5	openai	1,486	1,479 / 1,492	21,279	Proprietary
9	gpt-5.5-high	openai	1,484	1,478 / 1,491	20,944	Proprietary
10	gpt-5.6-sol-xhigh	openai	1,483	1,474 / 1,492	4,818	Proprietary
11	claude-sonnet-4-6	anthropic	1,482	1,476 / 1,488	57,813	Proprietary
12	claude-opus-4-8-high	anthropic	1,475	1,468 / 1,482	11,551	Proprietary
13	gpt-5.6-terra-xhigh	openai	1,472	1,463 / 1,480	5,787	Proprietary
14	gpt-5.4	openai	1,471	1,465 / 1,477	33,331	Proprietary
15	muse-spark-1.3-max	meta	1,471	1,452 / 1,489	1,006	Proprietary
16	gpt-6-astra-max	openai	1,468	1,453 / 1,482	1,621	Proprietary
17	claude-sonnet-5-high	anthropic	1,466	1,458 / 1,474	7,411	Proprietary
18	muse-spark-1.1	meta	1,465	1,456 / 1,474	4,885	Proprietary
19	claude-opus-4-8	anthropic	1,464	1,457 / 1,471	12,128	Proprietary
20	gemini-3.5-flash-medium	google	1,463	1,455 / 1,471	6,500	Proprietary
21	claude-opus-4-5-20251101	anthropic	1,462	1,452 / 1,473	7,981	Proprietary
22	gemini-3.5-flash-high	google	1,461	1,452 / 1,471	4,061	Proprietary
23	gpt-5.6-luna-xhigh	openai	1,457	1,449 / 1,465	5,766	Proprietary
24	gemini-3.6-flash-high	google	1,456	1,445 / 1,467	2,975	Proprietary
25	grok-4.6-high	xai	1,452	1,440 / 1,464	2,258	Proprietary

अन्य लीडरबोर्ड

LiveBench

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

स्थान	मॉडल	स्कोर
1	claude-fable-5-1-max-effort	83.8
2	claude-fable-5-max-effort	83.4
3	gpt-6-astra-max	83.1
4	muse-spark-1.3-xhigh	82.4
5	gpt-5.6-sol-max	81.7
6	deepseek-v4.1-flash-max	81.5
7	gpt-5.5-xhigh	80.8
8	claude-opus-5-max-effort	80.5
9	gemini-3.7-flash-high	79.9
10	smaug-agentic	79.7
11	qwen3.8-max	79.5
12	kimi-k3	79.5
13	grok-4.6	79
14	muse-spark-1.2-xhigh	78.9
15	gpt-5.4-xhigh	78.8

Aider polyglot (coding)

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

स्थान	मॉडल	स्कोर
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

BenchLM

मीट्रिक: aggregated display score · benchlm.ai

स्थान	मॉडल	संगठन	स्कोर
1	Claude Fable 5.1	Anthropic	84.6
2	GPT-6 Astra	OpenAI	83.8
3	Claude Opus 5	Anthropic	81.9
4	Claude Fable 5	Anthropic	81.7
5	GPT-5.6 Sol	OpenAI	80.7
6	Gemini 3.8 Flash	Google	75.8
7	Kimi K3	Moonshot AI	74.4
8	Qwen3.8 Max	Alibaba	73.3
9	Claude Opus 4.8	Anthropic	72.2
10	GPT-5.5	OpenAI	71.9
11	GPT-5.6 Terra	OpenAI	71.4
12	GPT-5.4	OpenAI	71.2
13	Claude Opus 4.7	Anthropic	70.9
14	Gemini 3.1 Pro	Google	70.5
15	Muse Spark 1.2	Meta	70.3

Artificial Analysis (Intelligence Index)

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

स्थान	मॉडल	संगठन	स्कोर
1	Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	53.4
2	Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	53.2
3	GPT-6 Astra (max)	OpenAI	52.7
4	GPT-6 Astra (xhigh)	OpenAI	52.4
5	Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	51.2
6	GPT-6 Astra (high)	OpenAI	50.9
7	Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	50.8
8	Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	49.7
9	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	49.6
10	GPT-6 Astra (medium)	OpenAI	49.6
11	Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	48.9
12	Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	48.1
13	Muse Spark 1.3 (max)	Meta	48.1
14	GPT-5.6 Sol (max)	OpenAI	47
15	Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	46.8

मूल्य और संदर्भ विंडो

स्रोत और पद्धति: OpenRouter

मूल्य और संदर्भ मेटाडेटा OpenRouter की सार्वजनिक API से। मूल्य USD में प्रति 1M टोकन।

मॉडल	संगठन	संदर्भ	इनपुट $/1M	आउटपुट $/1M	ज्ञान कटऑफ़
Auto Router	openrouter	2,000,000	$-1,000,000	$-1,000,000
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	x-ai	2,000,000	$1.25	$2.5	2025-09-01
SpaceXAI: Grok 4.20 Multi-Agent	x-ai	2,000,000	$1.25	$2.5	2025-09-01
DeepSeek: DeepSeek V4 Flash 0731	deepseek	1,310,720	$0.04	$0.64
DeepSeek: DeepSeek V4 Flash Latest	~deepseek	1,310,720	$0.03	$1
Meta: Llama 4 Scout	meta-llama	1,310,720	$0.1	$0.3	2024-08-31
Z.ai: GLM 5.3	z-ai	1,310,720	$0.65	$2.05
Z.ai: GLM 5.3 Flash	z-ai	1,310,720	$0.15	$0.5
Z.ai: GLM Flash Latest	~z-ai	1,310,720	$0.08	$0.25
Z.ai: GLM Latest	~z-ai	1,310,720	$0.65	$2.05
OpenAI: GPT Astra Latest	~openai	1,050,000	$10	$50
OpenAI: GPT Luna Latest	~openai	1,050,000	$0.2	$1.2	2026-02-16
OpenAI: GPT Sol Latest	~openai	1,050,000	$2	$10	2026-02-16
OpenAI: GPT Terra Latest	~openai	1,050,000	$2	$12	2026-02-16
OpenAI: GPT-5.4	openai	1,050,000	$2.5	$15
OpenAI: GPT-5.4 (batch)	openai	1,050,000	$1.25	$7.5
OpenAI: GPT-5.4 Pro	openai	1,050,000	$30	$180
OpenAI: GPT-5.4 Pro (batch)	openai	1,050,000	$15	$90

हाल के बदलाव

बदलाव ट्रैकिंग अगले दैनिक स्नैपशॉट से शुरू होती है। स्थान और स्कोर की चाल यहाँ सूचीबद्ध होंगी।

स्रोत और पद्धति

रैंकिंग सामुदायिक खुली मूल्यांकन से एकत्रित की जाती हैं। Elo स्कोर, विश्वास अंतराल और वोट LMArena से आते हैं (सामुदायिक मतदान वाले मॉडल युद्ध, खुले डेटासेट के रूप में प्रकाशित)। मूल्य और संदर्भ मेटाडेटा OpenRouter की सार्वजनिक API से आते हैं। Wikiprompt दैनिक स्नैपशॉट लेता है और इतिहास संरक्षित करता है; हम अपना मूल्यांकन नहीं चलाते।