All General Coding Reasoning Multimodal Safety Specialized Agentic Language Long Context Speed Text-to-Image Image Editing Text-to-Video Image-to-Video
AGIEval ARC Artificial Analysis Intelligence Index689 Chatbot Arena ELO282 GDPval-AA HellaSwag Humanity's Last Exam661 IFBench449 LiveBench MMLU MMLU-Pro349 MMLU-Pro (Open LLM Leaderboard)2839 WinoGrande

Chatbot Arena ELO

General

ELO rating from pairwise human preference voting on LMSYS Chatbot Arena

Source ↗ Higher is better

Rank Model Provider Elo
1 gemini-3-pro Google
1,487
2 Google: Gemini 2.5 ProRetiring Google
1,464
4 Anthropic: Claude Opus 4.5 Anthropic
1,446
8 ↳claude-opus-4-5-20251101-thinking-32k Anthropic
1,442
6 ernie-5.0-preview-1103 Baidu
1,446
7 grok-4.1 SpaceXAI
1,443
3 ↳grok-4.1-thinking SpaceXAI
1,451
9 Z.ai: GLM 4.6 Z.ai
1,441
10 qwen3-max-preview Alibaba
1,438
11 mistral-large-3 Mistral AI
1,432
12 mistral-medium-2508 Mistral AI
1,430
13 Z.ai: GLM 4.5Retiring Z.ai
1,428
14 chatgpt-4o-latest-20250326 OpenAI
1,427
16 Anthropic: Claude Sonnet 4.5 Anthropic
1,427
15 ↳claude-sonnet-4-5-20250929-thinking-32k Anthropic
1,427
17 DeepSeek: R1 0528 DeepSeek
1,426
18 grok-3-preview-02-24 SpaceXAI
1,424
19 DeepSeek: DeepSeek V3.2 ExpHistorical DeepSeek
1,424
22 ↳deepseek-v3.2-exp-thinking DeepSeek
1,422
20 longcat-flash-chat Meituan
1,423
21 Qwen: Qwen3 VL 235B A22B Instruct Alibaba
1,422
23 OpenAI: GPT-5.1 OpenAI
1,421
5 ↳GPT-5.1 (high) OpenAI
1,446
25 deepseek-v3.1 DeepSeek
1,419
33 ↳deepseek-v3.1-thinking DeepSeek
1,417
26 DeepSeek: DeepSeek V3.1 TerminusHistorical DeepSeek
1,419
30 ↳deepseek-v3.1-terminus-thinking DeepSeek
1,417
27 qwen3-235b-a22b-instruct-2507 Alibaba
1,419
28 Qwen: Qwen3 Next 80B A3B InstructHistorical Alibaba
1,418
29 gpt-4.5-preview-2025-02-27 OpenAI
1,417
32 DeepSeek: DeepSeek V3.2Historical DeepSeek
1,417
31 ↳deepseek-v3.2-thinking DeepSeek
1,417
34 Google: Gemini 2.5 FlashRetiring Google
1,415
35 qwen3-max-2025-09-23 Alibaba
1,414
36 Qwen: Qwen3 235B A22B Thinking 2507Historical Alibaba
1,413
37 Anthropic: Claude Opus 4.1 Anthropic
1,413
24 ↳claude-opus-4-1-20250805-thinking-16k Anthropic
1,420
38 o3-2025-04-16 OpenAI
1,411
39 kimi-k2-thinking-turbo Moonshot AI
1,410
40 grok-4-1-fast-reasoning SpaceXAI
1,409
41 Grok 4 SpaceXAI
1,409
42 grok-4-fast-chat SpaceXAI
1,408
43 GPT-5 (high) OpenAI
1,407
44 gemini-2.5-flash-preview-09-2025 Google
1,407
45 hunyuan-vision-1.5-thinking Tencent
1,404
46 gpt-5-chat OpenAI
1,403
47 Qwen: Qwen3 VL 235B A22B ThinkingHistorical Alibaba
1,401
48 hunyuan-t1-20250711 Tencent
1,398
49 amazon-nova-experimental-chat-10-20 Amazon
1,397
50 grok-4-fast-reasoning SpaceXAI
1,396

Access this data

JSON GET /api/v1 
[
  {
    "rank": 1,
    "model": "gemini-3-pro",
    "provider": "Google",
    "score": "1486.6027120272704"
  },
  {
    "rank": 2,
    "model": "Google: Gemini 2.5 Pro",
    "provider": "Google",
    "score": "1464.461788215414"
  },
  {
    "rank": 3,
    "model": "grok-4.1-thinking",
    "provider": "SpaceXAI",
    "score": "1451.2104783024167"
  }
]
Curl 
$ curl -s https://rightrank.ai/api/v1/rankings/chatbot-arena-elo.json | jq '.[:3]'
CLI brew install rightrank 
$ rightrank top chatbot-arena-elo --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category chatbot-arena-elo
$ rightrank value chatbot-arena-elo  # best performance per dollar
Claude Code Skill Skill 
# In Claude Code, use the RightRank skill:
/rightrank best model for chatbot-arena-elo
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on chatbot-arena-elo