All General Coding Reasoning Multimodal Safety Specialized Agentic Language Long Context Speed Text-to-Image Image Editing Text-to-Video Image-to-Video
AIME194 AIME 2025270 ARC-AGI Artificial Analysis Math Index270 BBH2839 Chatbot Arena Math274 FrontierMath GPQA (Open LLM Leaderboard)2839 GPQA Diamond615 GSM8K LogiQA MATH MATH Level 52839 MATH-500202 MuSR2839

Chatbot Arena Math

Reasoning

Source ↗ Higher is better

Rank Model Provider Elo
1 gemini-3-pro Google
1,474
2 Anthropic: Claude Opus 4.5 Anthropic
1,472
3 ↳claude-opus-4-5-20251101-thinking-32k Anthropic
1,460
4 GPT-5.1 (high) OpenAI
1,460
5 Google: Gemini 2.5 ProRetiring Google
1,459
7 longcat-flash-chat Meituan
1,450
8 qwen3-max-preview Alibaba
1,450
9 Qwen: Qwen3 Next 80B A3B InstructHistorical Alibaba
1,446
10 qwen3-max-2025-09-23 Alibaba
1,444
11 Z.ai: GLM 4.6 Z.ai
1,442
12 qwen3-235b-a22b-instruct-2507 Alibaba
1,441
13 DeepSeek: DeepSeek V3.2Historical DeepSeek
1,439
40 ↳deepseek-v3.2-thinking DeepSeek
1,413
15 Grok 4 SpaceXAI
1,432
16 o3-2025-04-16 OpenAI
1,432
17 Z.ai: GLM 4.5Retiring Z.ai
1,431
19 Qwen: Qwen3 VL 235B A22B Instruct Alibaba
1,425
21 gemini-2.5-flash-preview-09-2025 Google
1,425
22 Anthropic: Claude Sonnet 4.5 Anthropic
1,424
6 ↳claude-sonnet-4-5-20250929-thinking-32k Anthropic
1,454
23 Anthropic: Claude Opus 4.1 Anthropic
1,424
14 ↳claude-opus-4-1-20250805-thinking-16k Anthropic
1,433
24 grok-4.1 SpaceXAI
1,424
18 ↳grok-4.1-thinking SpaceXAI
1,430
25 kimi-k2-thinking-turbo Moonshot AI
1,423
26 amazon-nova-experimental-chat-10-20 Amazon
1,423
27 Qwen: Qwen3 VL 235B A22B ThinkingHistorical Alibaba
1,422
28 deepseek-v3.1 DeepSeek
1,422
31 ↳deepseek-v3.1-thinking DeepSeek
1,420
29 DeepSeek: DeepSeek V3.2 ExpHistorical DeepSeek
1,421
20 ↳deepseek-v3.2-exp-thinking DeepSeek
1,425
30 ernie-5.0-preview-1103 Baidu
1,420
32 grok-4-fast-chat SpaceXAI
1,418
33 amazon-nova-experimental-chat-10-09 Amazon
1,418
34 deepseek-v3.1-terminus-thinking DeepSeek
1,416
35 Google: Gemini 2.5 FlashRetiring Google
1,416
36 gpt-4.5-preview-2025-02-27 OpenAI
1,415
37 mistral-large-3 Mistral AI
1,415
38 Qwen: Qwen3 235B A22B Thinking 2507Historical Alibaba
1,415
39 mistral-medium-2508 Mistral AI
1,414
41 gpt-5-chat OpenAI
1,410
42 hunyuan-t1-20250711 Tencent
1,409
43 mai-1-preview Microsoft
1,407
44 Qwen: Qwen3 Next 80B A3B ThinkingHistorical Alibaba
1,405
45 GPT-5 (high) OpenAI
1,404
46 chatgpt-4o-latest-20250326 OpenAI
1,404
47 DeepSeek: R1 0528 DeepSeek
1,403
48 Qwen: Qwen3 32B Alibaba
1,403
49 Qwen: Qwen3 235B A22BHistorical Alibaba
1,403
50 Z.ai: GLM 4.5 Air Z.ai
1,403

Access this data

JSON GET /api/v1 
[
  {
    "rank": 1,
    "model": "gemini-3-pro",
    "provider": "Google",
    "score": "1473.8238348350305"
  },
  {
    "rank": 2,
    "model": "Anthropic: Claude Opus 4.5",
    "provider": "Anthropic",
    "score": "1472.1514290293894"
  },
  {
    "rank": 3,
    "model": "claude-opus-4-5-20251101-thinking-32k",
    "provider": "Anthropic",
    "score": "1460.1924180301814"
  }
]
Curl 
$ curl -s https://rightrank.ai/api/v1/rankings/chatbot-arena-math.json | jq '.[:3]'
CLI brew install rightrank 
$ rightrank top chatbot-arena-math --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category chatbot-arena-math
$ rightrank value chatbot-arena-math  # best performance per dollar
Claude Code Skill Skill 
# In Claude Code, use the RightRank skill:
/rightrank best model for chatbot-arena-math
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on chatbot-arena-math