Vision arena

From Wikiprompt, the free prompt encyclopedia

Community Elo leaderboard, aggregated daily from LMArena head-to-head battles. Overall arena first, then per-category breakdowns.

Last updated: 2026-08-24 · 147 models

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-fable-5	anthropic	1,328	1,319 / 1,337	9,562	Proprietary
2	claude-opus-5-high	anthropic	1,323	1,314 / 1,331	7,049	Proprietary
3	claude-opus-4-7	anthropic	1,317	1,310 / 1,323	21,445	Proprietary
4	claude-opus-4-7-high	anthropic	1,316	1,309 / 1,322	21,122	Proprietary
5	qwen3.8-max	alibaba	1,315	1,306 / 1,323	6,743	Proprietary
6	claude-opus-4-6-high	anthropic	1,315	1,308 / 1,321	20,867	Proprietary
7	gemini-3.5-flash-high	google	1,313	1,304 / 1,321	7,586	Proprietary
8	claude-opus-4-6	anthropic	1,311	1,305 / 1,318	25,169	Proprietary
9	gemini-3.5-flash-medium	google	1,308	1,300 / 1,317	7,533	Proprietary
10	muse-spark	meta	1,306	1,297 / 1,316	5,582	Proprietary
11	gemini-3-pro	google	1,305	1,298 / 1,313	13,134	Proprietary
12	muse-spark-1.2 (xHigh)	meta	1,304	1,290 / 1,319	1,853	Proprietary
13	gemini-3.6-flash-high	google	1,302	1,290 / 1,314	3,119	Proprietary
14	gpt-5.4-high	openai	1,297	1,290 / 1,304	22,515	Proprietary
15	gpt-5.5	openai	1,295	1,289 / 1,302	20,727	Proprietary
16	muse-spark-1.1	meta	1,295	1,286 / 1,303	6,142	Proprietary
17	gemini-3.1-pro-preview	google	1,294	1,288 / 1,300	38,674	Proprietary
18	claude-opus-4-8-high	anthropic	1,293	1,286 / 1,301	12,894	Proprietary
19	gpt-5.5-high	openai	1,293	1,286 / 1,300	19,406	Proprietary
20	gpt-5.4	openai	1,293	1,286 / 1,300	21,227	Proprietary
21	grok-4.5	xai	1,291	1,282 / 1,301	5,722	Proprietary
22	claude-opus-4-8	anthropic	1,287	1,280 / 1,295	13,354	Proprietary
23	gemini-3-flash	google	1,283	1,278 / 1,288	36,437	Proprietary
24	claude-sonnet-4-6	anthropic	1,281	1,275 / 1,288	25,559	Proprietary
25	claude-sonnet-5-high	anthropic	1,281	1,273 / 1,290	7,862	Proprietary
26	kimi-k2.6	moonshot	1,281	1,274 / 1,288	15,381	Modified MIT
27	qwen3.8-27b	alibaba	1,281	1,268 / 1,294	2,446	Apache 2.0
28	qwen3.7-plus	alibaba	1,281	1,272 / 1,289	8,627	Proprietary
29	gpt-5.6-sol-xhigh	openai	1,275	1,266 / 1,285	5,164	Proprietary
30	dola-seed-2.0-pro	bytedance	1,275	1,268 / 1,283	10,280	Proprietary
31	gemma-4-31b	google	1,275	1,268 / 1,281	33,890	Apache 2.0
32	gemini-3.5-flash-lite	google	1,272	1,261 / 1,284	3,165	Proprietary
33	gpt-5.6-terra-xhigh	openai	1,269	1,259 / 1,279	5,094	Proprietary
34	gpt-5.2-chat-latest-20260210	openai	1,267	1,261 / 1,274	15,370	Proprietary
35	kimi-k2.5-thinking	moonshot	1,267	1,261 / 1,273	26,666	Modified MIT
36	gemini-3-flash (thinking-minimal)	google	1,265	1,260 / 1,271	34,878	Proprietary
37	qwen3.5-397b-a17b	alibaba	1,265	1,259 / 1,271	25,396	Apache 2.0
38	glm-5v-turbo	zai	1,264	1,258 / 1,269	32,772	Proprietary
39	grok-4.20-beta-0309-reasoning	xai	1,264	1,257 / 1,270	25,114	Proprietary
40	gemini-2.5-pro	google	1,262	1,257 / 1,267	88,746	Proprietary
41	grok-4.20-multi-agent-beta-0309	xai	1,261	1,254 / 1,267	22,919	Proprietary
42	gemma-4-26b-a4b	google	1,259	1,253 / 1,266	22,719	Apache 2.0
43	minimax-m3	minimax	1,255	1,247 / 1,263	12,732	MiniMax Community License
44	kimi-k2.5-instant	moonshot	1,255	1,244 / 1,266	3,851	Modified MIT
45	gpt-5.6-luna-xhigh	openai	1,254	1,244 / 1,263	5,155	Proprietary
46	gpt-5.5-instant	openai	1,251	1,242 / 1,260	7,227	Proprietary
47	gemini-2.5-flash-preview-09-2025	google	1,249	1,239 / 1,259	4,697	Proprietary
48	gpt-5.1-high	openai	1,249	1,241 / 1,257	9,184	Proprietary
49	mimo-v2.5	xiaomi	1,249	1,242 / 1,255	22,457	MIT
50	ernie-5.0-preview-1220	baidu	1,248	1,237 / 1,259	3,161	Proprietary
51	qwen3-vl-235b-a22b-instruct	alibaba	1,247	1,240 / 1,254	12,138	Apache 2.0
52	gpt-5.2-high	openai	1,247	1,240 / 1,253	17,865	Proprietary
53	qwen3.5-122b-a10b	alibaba	1,246	1,239 / 1,253	12,453	Apache 2.0
54	gpt-5.4-mini-high	openai	1,245	1,239 / 1,252	24,061	Proprietary
55	chatgpt-4o-latest-20250326	openai	1,245	1,239 / 1,250	23,268	Proprietary
56	qwen3.5-27b	alibaba	1,241	1,235 / 1,248	23,081	Apache 2.0
57	gemini-3.1-flash-lite-preview	google	1,240	1,234 / 1,246	25,899	Proprietary
58	gemini-2.5-flash	google	1,236	1,231 / 1,240	59,372	Proprietary
59	Inkling Small	thinky	1,233	1,221 / 1,245	2,996	Apache 2.0
60	gpt-5.1	openai	1,233	1,225 / 1,241	10,027	Proprietary
61	gpt-5-chat	openai	1,232	1,225 / 1,239	40,317	Proprietary
62	gpt-5.2	openai	1,230	1,223 / 1,236	18,914	Proprietary
63	mimo-v2-omni	xiaomi	1,229	1,221 / 1,236	10,088	Proprietary
64	grok-4.3	xai	1,228	1,221 / 1,235	20,041	Proprietary
65	mistral-large-3	mistral	1,225	1,214 / 1,235	4,241	Apache 2.0
66	mistral-medium-3.5	mistral	1,222	1,212 / 1,232	5,098	Modified MIT
67	o3-2025-04-16	openai	1,216	1,209 / 1,222	46,249	Proprietary
68	qwen-vl-max-2025-08-13	alibaba	1,214	1,202 / 1,226	3,216	Proprietary
69	gpt-5-high	openai	1,211	1,204 / 1,218	34,690	Proprietary
70	gpt-4.1-2025-04-14	openai	1,210	1,203 / 1,217	41,710	Proprietary
71	grok-4-0709	xai	1,209	1,202 / 1,216	32,373	Proprietary
72	qwen3-vl-235b-a22b-thinking	alibaba	1,208	1,196 / 1,220	2,356	Apache 2.0
73	gpt-5-mini-high	openai	1,203	1,195 / 1,211	29,292	Proprietary
74	grok-4-1-fast-reasoning	xai	1,200	1,193 / 1,207	12,466	Proprietary
75	gemini-2.5-flash-lite-preview-09-2025-no-thinking	google	1,199	1,189 / 1,208	4,755	Proprietary
76	gpt-5.4-nano-high	openai	1,198	1,191 / 1,204	23,917	Proprietary
77	gpt-4.5-preview-2025-02-27	openai	1,195	1,184 / 1,207	2,925	Proprietary
78	o4-mini-2025-04-16	openai	1,195	1,188 / 1,202	41,968	Proprietary
79	claude-sonnet-4-20250514-thinking-32k	anthropic	1,193	1,176 / 1,209	1,159	Proprietary
80	claude-opus-4-20250514-thinking-16k	anthropic	1,191	1,175 / 1,207	1,300	Proprietary
81	gemini-2.5-flash-lite-preview-06-17-thinking	google	1,188	1,180 / 1,195	36,444	Proprietary
82	step-1o-turbo-202506	stepfun	1,187	1,172 / 1,201	1,921	Proprietary
83	hunyuan-large-vision	tencent	1,183	1,167 / 1,200	1,289	Proprietary
84	hunyuan-vision-1.5-thinking	tencent	1,183	1,171 / 1,195	2,397	Proprietary
85	gpt-4.1-mini-2025-04-14	openai	1,182	1,175 / 1,190	40,954	Proprietary
86	step-3	stepfun	1,177	1,165 / 1,188	3,279	Apache 2.0
87	claude-sonnet-4-20250514	anthropic	1,176	1,162 / 1,190	1,827	Proprietary
88	claude-opus-4-20250514	anthropic	1,175	1,163 / 1,188	2,201	Proprietary
89	mistral-medium-2508	mistral	1,172	1,166 / 1,178	41,789	Proprietary
90	claude-3-7-sonnet-20250219-thinking-32k	anthropic	1,171	1,156 / 1,186	1,452	Proprietary
91	o1-2024-12-17	openai	1,169	1,158 / 1,179	3,694	Proprietary
92	glm-4.6v	zai	1,166	1,153 / 1,180	2,323	MIT
93	gemma-3-27b-it	google	1,165	1,157 / 1,173	17,216	Gemma
94	gpt-5-nano-high	openai	1,162	1,151 / 1,173	3,984	Proprietary
95	gemini-1.5-pro-002	google	1,162	1,153 / 1,171	8,902	Proprietary
96	gemini-2.0-flash-001	google	1,159	1,151 / 1,166	10,168	Proprietary
97	mistral-medium-2505	mistral	1,158	1,149 / 1,166	10,938	Proprietary
98	glm-4.5v	zai	1,156	1,145 / 1,168	3,284	MIT
99	qwen2.5-vl-32b-instruct	alibaba	1,153	1,137 / 1,168	1,490	Apache 2.0
100	claude-3-7-sonnet-20250219	anthropic	1,151	1,142 / 1,160	4,539	Proprietary

By category

Ocr

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-fable-5	anthropic	1,339	1,331 / 1,348	6,864	Proprietary
2	claude-opus-5-high	anthropic	1,333	1,324 / 1,342	4,815	Proprietary
3	claude-opus-4-7	anthropic	1,326	1,319 / 1,333	15,535	Proprietary
4	claude-opus-4-6-high	anthropic	1,326	1,319 / 1,333	14,932	Proprietary
5	claude-opus-4-6	anthropic	1,325	1,319 / 1,332	18,261	Proprietary
6	qwen3.8-max	alibaba	1,324	1,315 / 1,333	4,769	Proprietary
7	claude-opus-4-7-high	anthropic	1,323	1,316 / 1,330	15,271	Proprietary
8	gemini-3.5-flash-medium	google	1,316	1,307 / 1,325	5,268	Proprietary
9	gemini-3.6-flash-high	google	1,315	1,301 / 1,328	2,099	Proprietary
10	gemini-3.5-flash-high	google	1,314	1,305 / 1,323	5,382	Proprietary
11	muse-spark-1.2 (xHigh)	meta	1,314	1,296 / 1,331	1,271	Proprietary
12	gemini-3-pro	google	1,311	1,302 / 1,319	8,055	Proprietary
13	gpt-5.4-high	openai	1,307	1,301 / 1,314	16,229	Proprietary
14	muse-spark	meta	1,307	1,297 / 1,317	4,022	Proprietary
15	claude-opus-4-8-high	anthropic	1,305	1,297 / 1,313	9,226	Proprietary

English

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-fable-5	anthropic	1,329	1,318 / 1,341	4,059	Proprietary
2	claude-opus-4-7	anthropic	1,321	1,312 / 1,330	9,228	Proprietary
3	claude-opus-4-7-high	anthropic	1,320	1,311 / 1,329	9,143	Proprietary
4	claude-opus-4-6-high	anthropic	1,319	1,310 / 1,328	8,897	Proprietary
5	claude-opus-5-high	anthropic	1,319	1,306 / 1,332	2,526	Proprietary
6	claude-opus-4-6	anthropic	1,316	1,307 / 1,324	10,897	Proprietary
7	qwen3.8-max	alibaba	1,310	1,297 / 1,324	2,224	Proprietary
8	gemini-3.5-flash-high	google	1,305	1,292 / 1,317	2,874	Proprietary
9	muse-spark	meta	1,302	1,288 / 1,316	2,332	Proprietary
10	muse-spark-1.1	meta	1,301	1,287 / 1,316	2,053	Proprietary
11	gemini-3.5-flash-medium	google	1,301	1,288 / 1,313	2,845	Proprietary
12	gemini-3.6-flash-high	google	1,297	1,279 / 1,315	1,151	Proprietary
13	claude-sonnet-4-6	anthropic	1,297	1,288 / 1,305	11,061	Proprietary
14	gpt-5.4-high	openai	1,295	1,286 / 1,304	9,328	Proprietary
15	gpt-5.5	openai	1,294	1,284 / 1,303	8,635	Proprietary

Diagram

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-fable-5	anthropic	1,366	1,354 / 1,378	2,647	Proprietary
2	claude-opus-5-high	anthropic	1,348	1,333 / 1,363	1,779	Proprietary
3	claude-opus-4-6	anthropic	1,340	1,331 / 1,349	6,827	Proprietary
4	claude-opus-4-7-high	anthropic	1,338	1,329 / 1,348	5,798	Proprietary
5	claude-opus-4-7	anthropic	1,337	1,327 / 1,346	5,930	Proprietary
6	qwen3.8-max	alibaba	1,332	1,317 / 1,347	1,724	Proprietary
7	claude-opus-4-6-high	anthropic	1,331	1,322 / 1,341	5,600	Proprietary
8	gpt-5.5	openai	1,324	1,314 / 1,333	5,676	Proprietary
9	gpt-5.4-high	openai	1,322	1,313 / 1,332	6,100	Proprietary
10	gemini-3.5-flash-high	google	1,320	1,306 / 1,334	2,019	Proprietary
11	grok-4.5	xai	1,319	1,304 / 1,335	1,527	Proprietary
12	muse-spark-1.2 (xHigh)	meta	1,319	1,292 / 1,346	505	Proprietary
13	gpt-5.4	openai	1,319	1,309 / 1,328	5,796	Proprietary
14	claude-opus-4-8-high	anthropic	1,317	1,306 / 1,328	3,561	Proprietary
15	gemini-3.5-flash-medium	google	1,317	1,303 / 1,331	1,995	Proprietary

Homework

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-fable-5	anthropic	1,356	1,338 / 1,375	1,124	Proprietary
2	claude-opus-5-high	anthropic	1,342	1,317 / 1,367	588	Proprietary
3	gemini-3.6-flash-high	google	1,341	1,304 / 1,377	263	Proprietary
4	claude-opus-4-8-high	anthropic	1,340	1,324 / 1,356	1,446	Proprietary
5	qwen3.8-max	alibaba	1,338	1,313 / 1,362	596	Proprietary
6	claude-opus-4-7-high	anthropic	1,337	1,325 / 1,349	2,913	Proprietary
7	claude-opus-4-7	anthropic	1,336	1,324 / 1,348	2,973	Proprietary
8	gpt-5.5-high	openai	1,336	1,324 / 1,349	2,601	Proprietary
9	claude-opus-4-6-high	anthropic	1,335	1,323 / 1,348	2,724	Proprietary
10	gpt-5.4-high	openai	1,335	1,323 / 1,347	2,985	Proprietary
11	gemini-3.5-flash-medium	google	1,330	1,308 / 1,352	737	Proprietary
12	gpt-5.5	openai	1,329	1,317 / 1,342	2,706	Proprietary
13	claude-opus-4-6	anthropic	1,328	1,317 / 1,339	3,576	Proprietary
14	claude-opus-4-8	anthropic	1,327	1,312 / 1,343	1,582	Proprietary
15	grok-4.5	xai	1,324	1,295 / 1,352	461	Proprietary

Chinese

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	claude-opus-5-high	anthropic	1,410	1,375 / 1,444	337	Proprietary
2	gemini-3.5-flash-high	google	1,388	1,356 / 1,419	427	Proprietary
3	gemini-3.5-flash-medium	google	1,388	1,355 / 1,420	389	Proprietary
4	claude-fable-5	anthropic	1,386	1,356 / 1,416	459	Proprietary
5	claude-opus-4-6	anthropic	1,381	1,360 / 1,401	1,380	Proprietary
6	gemini-3-pro	google	1,378	1,358 / 1,397	1,412	Proprietary
7	gpt-5.6-terra-xhigh	openai	1,374	1,337 / 1,412	256	Proprietary
8	claude-opus-4-6-high	anthropic	1,373	1,352 / 1,394	1,209	Proprietary
9	claude-opus-4-7	anthropic	1,369	1,348 / 1,389	1,255	Proprietary
10	gemini-3.1-pro-preview	google	1,367	1,350 / 1,384	2,185	Proprietary
11	muse-spark-1.1	meta	1,365	1,329 / 1,400	342	Proprietary
12	claude-opus-4-7-high	anthropic	1,359	1,338 / 1,380	1,139	Proprietary
13	gpt-5.4-high	openai	1,357	1,336 / 1,378	1,249	Proprietary
14	gpt-5.5-high	openai	1,356	1,334 / 1,379	1,000	Proprietary
15	muse-spark	meta	1,356	1,326 / 1,387	450	Proprietary

Creative writing vision

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	gemini-3-pro	google	1,348	1,329 / 1,367	1,040	Proprietary
2	claude-fable-5	anthropic	1,340	1,315 / 1,364	632	Proprietary
3	claude-opus-4-6-high	anthropic	1,332	1,314 / 1,350	1,201	Proprietary
4	muse-spark	meta	1,331	1,297 / 1,365	329	Proprietary
5	claude-opus-4-7-high	anthropic	1,323	1,305 / 1,341	1,231	Proprietary
6	gemini-3.1-pro-preview	google	1,322	1,309 / 1,336	2,311	Proprietary
7	claude-opus-4-6	anthropic	1,317	1,300 / 1,333	1,488	Proprietary
8	qwen3.8-max	alibaba	1,315	1,285 / 1,345	407	Proprietary
9	claude-opus-4-7	anthropic	1,311	1,293 / 1,329	1,201	Proprietary
10	claude-opus-4-8-high	anthropic	1,308	1,286 / 1,330	807	Proprietary
11	gemini-3.5-flash-medium	google	1,304	1,275 / 1,333	439	Proprietary
12	gpt-5.5-high	openai	1,299	1,281 / 1,317	1,207	Proprietary
13	gemini-3-flash	google	1,298	1,285 / 1,311	2,329	Proprietary
14	claude-opus-5-high	anthropic	1,295	1,269 / 1,320	603	Proprietary
15	gemini-3.5-flash-high	google	1,291	1,263 / 1,318	524	Proprietary

Humor

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	muse-spark	meta	1,346	1,305 / 1,387	227	Proprietary
2	gemini-3-pro	google	1,338	1,313 / 1,363	557	Proprietary
3	claude-fable-5	anthropic	1,330	1,297 / 1,364	316	Proprietary
4	gemini-3.1-pro-preview	google	1,326	1,310 / 1,342	1,468	Proprietary
5	claude-opus-4-6	anthropic	1,319	1,299 / 1,340	914	Proprietary
6	claude-opus-4-7-high	anthropic	1,309	1,287 / 1,332	782	Proprietary
7	claude-opus-4-6-high	anthropic	1,309	1,286 / 1,331	770	Proprietary
8	gemini-3.5-flash-high	google	1,309	1,270 / 1,347	253	Proprietary
9	gemini-3.5-flash-medium	google	1,304	1,264 / 1,344	237	Proprietary
10	claude-opus-4-7	anthropic	1,303	1,282 / 1,325	785	Proprietary
11	qwen3.8-max	alibaba	1,294	1,253 / 1,335	216	Proprietary
12	claude-opus-4-8-high	anthropic	1,292	1,264 / 1,320	472	Proprietary
13	gpt-5.5-high	openai	1,292	1,269 / 1,314	701	Proprietary
14	claude-opus-5-high	anthropic	1,289	1,252 / 1,326	264	Proprietary
15	qwen3.7-plus	alibaba	1,288	1,255 / 1,321	313	Proprietary

Creative writing

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	gemini-3-pro	google	1,391	1,368 / 1,413	766	Proprietary
2	ernie-5.0-preview-1220	baidu	1,336	1,291 / 1,381	176	Proprietary
3	gemini-3-flash	google	1,306	1,267 / 1,346	217	Proprietary
4	gpt-5.1	openai	1,291	1,262 / 1,321	411	Proprietary
5	gemini-2.5-flash-preview-09-2025	google	1,289	1,264 / 1,313	555	Proprietary
6	gpt-5.1-high	openai	1,282	1,252 / 1,313	385	Proprietary
7	gemini-2.5-pro	google	1,277	1,264 / 1,291	2,418	Proprietary
8	grok-4-0709	xai	1,265	1,249 / 1,282	1,461	Proprietary
9	claude-opus-4-20250514	anthropic	1,253	1,221 / 1,286	192	Proprietary
10	gemini-2.5-flash	google	1,253	1,238 / 1,268	1,745	Proprietary
11	chatgpt-4o-latest-20250326	openai	1,248	1,230 / 1,266	1,047	Proprietary
12	gpt-5-chat	openai	1,239	1,224 / 1,255	1,518	Proprietary
13	qwen3-vl-235b-a22b-thinking	alibaba	1,230	1,192 / 1,268	219	Apache 2.0
14	qwen3-vl-235b-a22b-instruct	alibaba	1,225	1,203 / 1,247	690	Apache 2.0
15	mistral-medium-2508	mistral	1,223	1,207 / 1,239	1,365	Proprietary

Entity recognition

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	gemini-3-pro	google	1,354	1,318 / 1,389	240	Proprietary
2	gemini-3-flash	google	1,334	1,302 / 1,365	319	Proprietary
3	gemini-3.1-pro-preview	google	1,327	1,297 / 1,358	334	Proprietary
4	gemini-3-flash (thinking-minimal)	google	1,312	1,281 / 1,343	295	Proprietary
5	gemini-3.1-flash-lite-preview	google	1,307	1,272 / 1,342	233	Proprietary
6	grok-4-0709	xai	1,288	1,253 / 1,322	340	Proprietary
7	grok-4.20-beta-0309-reasoning	xai	1,287	1,242 / 1,331	151	Proprietary
8	kimi-k2.5-thinking	moonshot	1,284	1,250 / 1,318	248	Modified MIT
9	gemini-2.5-pro	google	1,283	1,261 / 1,305	903	Proprietary
10	claude-opus-4-6-high	anthropic	1,278	1,228 / 1,327	104	Proprietary
11	qwen3.5-397b-a17b	alibaba	1,278	1,238 / 1,317	187	Apache 2.0
12	grok-4.20-multi-agent-beta-0309	xai	1,264	1,220 / 1,307	149	Proprietary
13	claude-opus-4-7-high	anthropic	1,263	1,221 / 1,305	139	Proprietary
14	gpt-5-high	openai	1,260	1,230 / 1,289	431	Proprietary
15	gpt-5.4	openai	1,259	1,208 / 1,309	117	Proprietary

Captioning

Rank	Model	Organization	Elo score	95% CI	Votes	License
1	gemini-3.1-pro-preview	google	1,336	1,286 / 1,386	122	Proprietary
2	gemini-3-pro	google	1,318	1,284 / 1,353	216	Proprietary
3	gemini-2.5-pro	google	1,302	1,280 / 1,325	793	Proprietary
4	gemma-4-26b-a4b	google	1,285	1,207 / 1,363	49	Apache 2.0
5	qwen3-vl-235b-a22b-instruct	alibaba	1,278	1,232 / 1,324	143	Apache 2.0
6	gemini-2.5-flash	google	1,278	1,254 / 1,302	582	Proprietary
7	gpt-5.2-high	openai	1,275	1,216 / 1,334	84	Proprietary
8	gemini-3-flash	google	1,274	1,233 / 1,314	174	Proprietary
9	gemini-3.1-flash-lite-preview	google	1,272	1,202 / 1,341	64	Proprietary
10	glm-5v-turbo	zai	1,269	1,186 / 1,351	43	Proprietary
11	kimi-k2.5-thinking	moonshot	1,253	1,201 / 1,306	109	Modified MIT
12	gpt-5.1-high	openai	1,243	1,187 / 1,299	98	Proprietary
13	grok-4-0709	xai	1,243	1,210 / 1,276	360	Proprietary
14	gemini-3-flash (thinking-minimal)	google	1,240	1,195 / 1,286	156	Proprietary
15	chatgpt-4o-latest-20250326	openai	1,223	1,188 / 1,258	277	Proprietary

Sources and methodology

Rankings above are aggregated from open community evaluations. Elo ratings, confidence intervals and vote counts come from LMArena (crowdsourced head-to-head model battles, published as an open dataset). Model pricing and context metadata come from the public OpenRouter API. Wikiprompt snapshots these sources daily and preserves the history; we run no proprietary evaluations of our own.