โ† Todos os benchmarks

Arena de visao

Da Wikiprompt, a enciclopedia livre de prompts

Ranking Elo da comunidade, agregado diariamente das batalhas da LMArena. Primeiro a arena geral, depois o detalhamento por categoria.

Ultima atualizacao: 2026-10-13 ยท 165 modelos

PosicaoModeloOrganizacaoPontuacao Elo
1claude-fable-5-highanthropic1,324
2claude-opus-5.5-highanthropic1,321
3claude-opus-5-highanthropic1,319
4claude-fable-5.1-maxanthropic1,318
5claude-opus-4-7anthropic1,316
6gemini-3.7-flash-highgoogle1,316
7claude-opus-4-6-highanthropic1,316
8gemini-3.8-flash-highgoogle1,314
9qwen3.8-maxalibaba1,314
10claude-opus-4-6anthropic1,313
11claude-opus-4-7-highanthropic1,313
12gemini-3.5-flash-highgoogle1,310
13muse-spark-1.3-maxmeta1,309
14gemini-3.5-flash-mediumgoogle1,309
15muse-sparkmeta1,306
16gemini-3-progoogle1,305
17muse-spark-1.2 (xHigh)meta1,305
18gpt-5.4-highopenai1,303
19muse-spark-1.3 (xHigh)meta1,301
20gemini-3.6-flash-highgoogle1,298
21gpt-5.5openai1,297
22gemini-3.1-pro-previewgoogle1,296
23glm-5.3-flashzai1,296
24claude-opus-4-8-highanthropic1,294
25muse-spark-1.1meta1,293
26gpt-5.5-highopenai1,292
27gpt-5.4openai1,292
28claude-sonnet-5.5-xhighanthropic1,289
29claude-opus-4-8anthropic1,289
30gpt-6.1-sol-maxopenai1,288
31grok-4.5xai1,288
32gemini-3-flashgoogle1,285
33kimi-k2.6moonshot1,283
34claude-sonnet-4-6anthropic1,282
35gpt-5.6-sol-xhighopenai1,281
36gpt-6-astra-maxopenai1,281
37qwen3.7-plusalibaba1,279
38gemma-4-31bgoogle1,277
39deepseek-v4.1-flash-maxdeepseek1,277
40dola-seed-2.0-probytedance1,274
41claude-sonnet-5-highanthropic1,274
42qwen3.8-27balibaba1,271
43gpt-5.6-terra-xhighopenai1,271
44kimi-k2.5-thinkingmoonshot1,269
45gemini-3.5-flash-litegoogle1,268
46gpt-5.2-chat-latest-20260210openai1,268
47Step 5 Previewstepfun1,267
48gemini-3-flash (thinking-minimal)google1,266
49glm-5v-turbozai1,264
50mimo-v2.6-proxiaomi1,264
51gemini-2.5-progoogle1,263
52grok-4.6-highxai1,263
53grok-4.20-beta-0309-reasoningxai1,263
54qwen3.5-397b-a17balibaba1,263
55gemma-4-26b-a4bgoogle1,260
56mimo-v2.6-flashxiaomi1,259
57grok-4.20-multi-agent-beta-0309xai1,259
58gpt-5.6-luna-xhighopenai1,258
59kimi-k2.5-instantmoonshot1,253
60minimax-m3minimax1,253
61gemini-2.5-flash-preview-09-2025google1,253
62gpt-5.5-instantopenai1,250
63gpt-5.1-highopenai1,250
64ernie-5.0-preview-1220baidu1,248
65mimo-v2.5xiaomi1,247
66qwen3-vl-235b-a22b-instructalibaba1,247
67gpt-5.2-highopenai1,246
68gpt-5.4-mini-highopenai1,245
69gpt-6-sol-maxopenai1,245
70qwen3.5-122b-a10balibaba1,245
71chatgpt-4o-latest-20250326openai1,243
72qwen3.5-27balibaba1,241
73gemini-3.1-flash-lite-previewgoogle1,240
74gemini-2.5-flashgoogle1,235
75Inkling Smallthinky1,235
76gpt-5.1openai1,235
77gpt-5-chatopenai1,232
78grok-4.3xai1,229
79gpt-5.2openai1,229
80grok-4.7-xhighxai1,228
81mimo-v2-omnixiaomi1,228
82mistral-medium-3.5mistral1,223
83mistral-large-3mistral1,221
84gpt-6-luna-maxopenai1,217
85o3-2025-04-16openai1,214
86qwen-vl-max-2025-08-13alibaba1,213
87gpt-4.1-2025-04-14openai1,211
88grok-4-0709xai1,210
89gpt-5-highopenai1,208
90qwen3-vl-235b-a22b-thinkingalibaba1,207
91gpt-5-mini-highopenai1,202
92grok-4-1-fast-reasoningxai1,201
93gemini-2.5-flash-lite-preview-09-2025-no-thinkinggoogle1,198
94gpt-5.4-nano-highopenai1,196
95gpt-4.5-preview-2025-02-27openai1,195
96o4-mini-2025-04-16openai1,194
97claude-opus-4-20250514-thinking-16kanthropic1,192
98claude-sonnet-4-20250514-thinking-32kanthropic1,191
99gemini-2.5-flash-lite-preview-06-17-thinkinggoogle1,187
100step-1o-turbo-202506stepfun1,186

Por categoria

Ocr

PosicaoModeloOrganizacaoPontuacao Elo
1claude-fable-5-highanthropic1,336
2gemini-3.8-flash-highgoogle1,334
3claude-opus-5-highanthropic1,329
4claude-opus-5.5-highanthropic1,327
5claude-opus-4-6anthropic1,327
6claude-fable-5.1-maxanthropic1,326
7claude-opus-4-7anthropic1,326
8claude-opus-4-6-highanthropic1,326
9gemini-3.7-flash-highgoogle1,324
10qwen3.8-maxalibaba1,323
11claude-opus-4-7-highanthropic1,320
12muse-spark-1.3-maxmeta1,318
13gemini-3.5-flash-mediumgoogle1,318
14gemini-3.5-flash-highgoogle1,313
15muse-spark-1.2 (xHigh)meta1,313

English

PosicaoModeloOrganizacaoPontuacao Elo
1claude-fable-5-highanthropic1,324
2claude-opus-4-6-highanthropic1,324
3claude-opus-4-7anthropic1,322
4claude-opus-4-7-highanthropic1,320
5claude-opus-4-6anthropic1,319
6claude-opus-5.5-highanthropic1,319
7claude-opus-5-highanthropic1,315
8gemini-3.8-flash-highgoogle1,313
9claude-fable-5.1-maxanthropic1,311
10qwen3.8-maxalibaba1,310
11gemini-3.7-flash-highgoogle1,308
12gemini-3.5-flash-highgoogle1,305
13muse-sparkmeta1,304
14gpt-5.4-highopenai1,301
15gemini-3.5-flash-mediumgoogle1,301

Diagram

PosicaoModeloOrganizacaoPontuacao Elo
1claude-fable-5-highanthropic1,355
2claude-opus-5-highanthropic1,348
3claude-fable-5.1-maxanthropic1,346
4gemini-3.8-flash-highgoogle1,345
5claude-opus-4-6anthropic1,340
6claude-opus-5.5-highanthropic1,339
7claude-opus-4-7-highanthropic1,336
8claude-opus-4-7anthropic1,335
9claude-opus-4-6-highanthropic1,332
10muse-spark-1.3-maxmeta1,330
11gemini-3.7-flash-highgoogle1,329
12claude-sonnet-5.5-xhighanthropic1,328
13gpt-5.4-highopenai1,327
14gpt-5.5openai1,325
15gemini-3.5-flash-mediumgoogle1,325

Homework

PosicaoModeloOrganizacaoPontuacao Elo
1claude-opus-5.5-highanthropic1,359
2claude-fable-5-highanthropic1,357
3gpt-6.1-sol-maxopenai1,352
4gemini-3.8-flash-highgoogle1,351
5claude-fable-5.1-maxanthropic1,346
6qwen3.8-maxalibaba1,343
7claude-opus-5-highanthropic1,342
8gpt-6-astra-maxopenai1,342
9gpt-5.4-highopenai1,338
10claude-opus-4-7-highanthropic1,337
11claude-opus-4-8-highanthropic1,337
12claude-opus-4-6-highanthropic1,336
13claude-opus-4-7anthropic1,334
14gpt-5.5-highopenai1,333
15gemini-3.7-flash-highgoogle1,332

Chinese

PosicaoModeloOrganizacaoPontuacao Elo
2claude-opus-5-highanthropic1,404
5gemini-3.5-flash-highgoogle1,378
7gemini-3.5-flash-mediumgoogle1,376
8claude-fable-5-highanthropic1,373
9claude-opus-4-6anthropic1,370
10claude-opus-4-7anthropic1,370
11gemini-3-progoogle1,370
12glm-5.3-flashzai1,367
13claude-opus-4-6-highanthropic1,366
14gemini-3.1-pro-previewgoogle1,365
17qwen3.8-maxalibaba1,361
18gpt-5.5openai1,360
19gpt-5.5-highopenai1,358
20claude-opus-4-7-highanthropic1,355
21gpt-5.4-highopenai1,353

Creative writing vision

PosicaoModeloOrganizacaoPontuacao Elo
1gemini-3-progoogle1,341
2claude-fable-5-highanthropic1,339
4claude-opus-4-6-highanthropic1,332
5claude-fable-5.1-maxanthropic1,329
6claude-opus-4-7-highanthropic1,325
7gemini-3.1-pro-previewgoogle1,324
8muse-sparkmeta1,324
9claude-opus-4-7anthropic1,320
10claude-opus-4-6anthropic1,319
11gemini-3-flashgoogle1,315
12gemini-3.7-flash-highgoogle1,314
13qwen3.8-maxalibaba1,314
14claude-opus-5-highanthropic1,312
15gemini-3.5-flash-mediumgoogle1,305
16gpt-5.5-highopenai1,302

Humor

PosicaoModeloOrganizacaoPontuacao Elo
2claude-fable-5-highanthropic1,341
3gemini-3-progoogle1,339
5gemini-3.1-pro-previewgoogle1,323
6gemini-3.5-flash-mediumgoogle1,322
7gemini-3.5-flash-highgoogle1,317
8claude-opus-4-6anthropic1,313
9claude-opus-4-6-highanthropic1,313
10claude-opus-4-7-highanthropic1,308
12qwen3.8-maxalibaba1,305
13claude-opus-4-7anthropic1,305
15claude-opus-5-highanthropic1,296
16gpt-5.5-highopenai1,293
17gemini-3-flashgoogle1,291
18gemini-3.6-flash-highgoogle1,289
19gpt-5.4-highopenai1,285

Creative writing

PosicaoModeloOrganizacaoPontuacao Elo
1gemini-3-progoogle1,391
4gpt-5.1openai1,291
5gemini-2.5-flash-preview-09-2025google1,289
6gpt-5.1-highopenai1,282
7gemini-2.5-progoogle1,277
8grok-4-0709xai1,265
10gemini-2.5-flashgoogle1,253
11chatgpt-4o-latest-20250326openai1,248
12gpt-5-chatopenai1,239
14qwen3-vl-235b-a22b-instructalibaba1,225
15mistral-medium-2508mistral1,223
16gpt-4.1-2025-04-14openai1,223
17gemini-2.5-flash-lite-preview-09-2025-no-thinkinggoogle1,220
18gemini-2.0-flash-001google1,205
19o3-2025-04-16openai1,197

Entity recognition

PosicaoModeloOrganizacaoPontuacao Elo
2gemini-3-flashgoogle1,335
3gemini-3.1-pro-previewgoogle1,329
4gemini-3-flash (thinking-minimal)google1,310
6grok-4-0709xai1,288
7kimi-k2.5-thinkingmoonshot1,284
8gemini-2.5-progoogle1,283
15gpt-5-highopenai1,262
16gemini-2.5-flashgoogle1,251
20chatgpt-4o-latest-20250326openai1,245
24o3-2025-04-16openai1,234
28gpt-5-mini-highopenai1,226
30gemma-4-31bgoogle1,224
32o4-mini-2025-04-16openai1,219
33gpt-5-chatopenai1,219
36gpt-4.1-2025-04-14openai1,208

Captioning

PosicaoModeloOrganizacaoPontuacao Elo
3gemini-2.5-progoogle1,304
7gemini-2.5-flashgoogle1,277
13grok-4-0709xai1,245
18gpt-5-mini-highopenai1,217
19gpt-5-chatopenai1,212
20o3-2025-04-16openai1,210
21gpt-4.1-2025-04-14openai1,207
22o4-mini-2025-04-16openai1,203
23gpt-5-highopenai1,203
24gemini-2.5-flash-lite-preview-06-17-thinkinggoogle1,185
26gpt-4.1-mini-2025-04-14openai1,173
31mistral-medium-2508mistral1,146

Veja tambem

Fontes e metodologia

Os rankings sao agregados de avaliacoes abertas da comunidade. Pontuacoes Elo, intervalos de confianca e votos vem da LMArena (batalhas de modelos votadas pela comunidade, publicadas como dataset aberto). Precos e metadata de contexto vem da API publica da OpenRouter. A Wikiprompt tira um snapshot diario e preserva o historico; nao rodamos avaliacoes proprias.

  1. LMArena leaderboard dataset (Hugging Face)
  2. LMArena leaderboard