Best AI Model

AI models ranked by quality. Arena ELO scores from crowdsourced human evaluations determine the overall ranking.

#ModelCreatorValueArena ELOInput/MProvidersType
1 Claude Opus 4.6 Anthropic ☆☆☆☆☆ 0.2 1504 $5.00 3 Chat
2 Claude Opus 4.5 Anthropic ☆☆☆☆☆ 0.1 1470 $5.00 2 Chat
3 Claude Sonnet 4.6 Anthropic ☆☆☆☆☆ 0.2 1460 $3.00 3 Chat
4 Claude Sonnet 4.5 Anthropic ☆☆☆☆☆ 0.2 1450 $3.00 2 Chat
5 Gemini 2.5 Pro Google ⯪☆☆☆☆ 0.4 1449 $1.25 2 Chat
6 Claude Opus 4 Anthropic ☆☆☆☆☆ 0.0 1446 $15.00 2 Chat
7 o3 OpenAI ⯪☆☆☆☆ 0.4 1440 $2.00 2 Reasoning
8 Claude Sonnet 4 Anthropic ☆☆☆☆☆ 0.2 1420 $3.00 1 Chat
9 Gemini 2.5 Flash Google ★⯪☆☆☆ 1.3 1411 $0.30 1 Chat
10 GPT-4.1 OpenAI ⯪☆☆☆☆ 0.3 1410 $2.00 2 Chat
11 Grok 3 xAI ☆☆☆☆☆ 0.2 1402 $3.00 1 Chat
12 o4 mini OpenAI ⯪☆☆☆☆ 0.6 1400 $1.10 1 Reasoning
13 DeepSeek R1 DeepSeek ★☆☆☆☆ 1.1 1398 $0.55 3 Reasoning
14 o1 OpenAI ☆☆☆☆☆ 0.0 1388 $15.00 1 Reasoning
15 Claude Haiku 4.5 Anthropic ⯪☆☆☆☆ 0.5 1380 $1.00 2 Chat
16 Grok 3 mini xAI ★★⯪☆☆ 2.5 1363 $0.30 1 Reasoning
17 Gemini 2.0 Flash Google ★★★★★ 5.0 1361 $0.10 1 Chat
18 DeepSeek V3 DeepSeek ★★★★⯪ 4.9 1358 $0.14 2 Chat
19 GPT-4.1 mini OpenAI ★☆☆☆☆ 1.2 1350 $0.40 1 Chat
20 o3 mini OpenAI ⯪☆☆☆☆ 0.4 1348 $1.10 1 Reasoning
21 GPT-4o OpenAI ☆☆☆☆☆ 0.2 1346 $2.50 2 Chat
22 Llama 4 Maverick Meta ★★⯪☆☆ 2.6 1327 $0.19 3 Chat
23 Claude Haiku 3.5 Anthropic ⯪☆☆☆☆ 0.4 1323 $0.80 2 Chat
24 Llama 4 Scout Meta ★★★★⯪ 4.4 1322 $0.10 3 Chat
25 GPT-4o mini OpenAI ★★⯪☆☆ 2.3 1310 $0.15 2 Chat
26 Mistral Large 3 Mistral ⯪☆☆☆☆ 0.8 1305 $0.50 2 Chat
27 Mistral Small 3.2 Mistral ★★★★⯪ 4.8 1280 $0.06 1 Chat