All General Coding Reasoning Multimodal Safety Specialized Agentic Language Long Context Speed Text-to-Image Image Editing Text-to-Video Image-to-Video
Artificial Analysis Coding Index259 Chatbot Arena Coding278 CodeElo HumanEval LiveCodeBench343 MBPP SWE-bench SWE-bench Verified SciCode229

Chatbot Arena Coding

Coding

Source ↗ Higher is better

Rank Model Provider Elo
2 Anthropic: Claude Opus 4.5 Anthropic
1,498
1 ↳claude-opus-4-5-20251101-thinking-32k Anthropic
1,515
4 gemini-3-pro Google
1,486
6 Anthropic: Claude Sonnet 4.5 Anthropic
1,476
3 ↳claude-sonnet-4-5-20250929-thinking-32k Anthropic
1,495
7 Anthropic: Claude Opus 4.1 Anthropic
1,470
5 ↳claude-opus-4-1-20250805-thinking-16k Anthropic
1,483
8 longcat-flash-chat Meituan
1,468
9 Google: Gemini 2.5 ProRetiring Google
1,459
10 qwen3-max-preview Alibaba
1,457
12 Z.ai: GLM 4.6 Z.ai
1,455
14 Anthropic: Claude Haiku 4.5 Anthropic
1,451
15 ernie-5.0-preview-1103 Baidu
1,449
16 kimi-k2-thinking-turbo Moonshot AI
1,448
17 grok-4.1 SpaceXAI
1,444
11 ↳grok-4.1-thinking SpaceXAI
1,456
18 qwen3-235b-a22b-instruct-2507 Alibaba
1,443
19 Qwen: Qwen3 Next 80B A3B InstructHistorical Alibaba
1,442
20 mistral-large-3 Mistral AI
1,442
21 Qwen: Qwen3 VL 235B A22B Instruct Alibaba
1,441
22 claude-opus-4-20250514-thinking-16k Anthropic
1,441
23 qwen3-max-2025-09-23 Alibaba
1,440
24 GPT-5 (high) OpenAI
1,439
25 OpenAI: GPT-5.1 OpenAI
1,439
13 ↳GPT-5.1 (high) OpenAI
1,451
26 DeepSeek: DeepSeek V3.2 ExpHistorical DeepSeek
1,438
29 ↳deepseek-v3.2-exp-thinking DeepSeek
1,436
28 DeepSeek: DeepSeek V3.2Historical DeepSeek
1,436
27 ↳deepseek-v3.2-thinking DeepSeek
1,436
30 Z.ai: GLM 4.5Retiring Z.ai
1,434
31 grok-3-preview-02-24 SpaceXAI
1,432
32 mistral-medium-2508 Mistral AI
1,431
33 Qwen: Qwen3 VL 235B A22B ThinkingHistorical Alibaba
1,427
34 grok-4-fast-chat SpaceXAI
1,426
35 DeepSeek: R1 0528 DeepSeek
1,426
36 deepseek-v3.1-terminus-thinking DeepSeek
1,424
37 Qwen: Qwen3 235B A22B Thinking 2507Historical Alibaba
1,423
38 Google: Gemini 2.5 FlashRetiring Google
1,422
39 grok-4-fast-reasoning SpaceXAI
1,420
41 hunyuan-vision-1.5-thinking Tencent
1,417
42 Qwen: Qwen3 30B A3B Instruct 2507 Alibaba
1,417
43 deepseek-v3.1 DeepSeek
1,415
40 ↳deepseek-v3.1-thinking DeepSeek
1,419
44 claude-sonnet-4-20250514-thinking-32k Anthropic
1,412
45 chatgpt-4o-latest-20250326 OpenAI
1,411
46 qwen3-coder-480b-a35b-instruct Alibaba
1,411
47 grok-4-1-fast-reasoning SpaceXAI
1,411
48 o3-2025-04-16 OpenAI
1,408
49 GPT-5 mini (high) OpenAI
1,408
50 Grok 4 SpaceXAI
1,407

Access this data

JSON GET /api/v1 
[
  {
    "rank": 1,
    "model": "claude-opus-4-5-20251101-thinking-32k",
    "provider": "Anthropic",
    "score": "1515.1020105121383"
  },
  {
    "rank": 2,
    "model": "Anthropic: Claude Opus 4.5",
    "provider": "Anthropic",
    "score": "1498.0523144292692"
  },
  {
    "rank": 3,
    "model": "claude-sonnet-4-5-20250929-thinking-32k",
    "provider": "Anthropic",
    "score": "1495.1706246068536"
  }
]
Curl 
$ curl -s https://rightrank.ai/api/v1/rankings/chatbot-arena-coding.json | jq '.[:3]'
CLI brew install rightrank 
$ rightrank top chatbot-arena-coding --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category chatbot-arena-coding
$ rightrank value chatbot-arena-coding  # best performance per dollar
Claude Code Skill Skill 
# In Claude Code, use the RightRank skill:
/rightrank best model for chatbot-arena-coding
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on chatbot-arena-coding