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

LiveCodeBench

Coding

Continuously updated coding problems to prevent data contamination

Higher is better

Rank Model Provider Score
1 Gemini 3 Pro Preview (high) Google
91.7%
2 Gemini 3 Flash Preview (Reasoning) Google
90.8%
3 DeepSeek V3.2 Speciale DeepSeek
89.6%
4 GPT-5.2 (medium) OpenAI
89.4%
5 GLM-4.7 (Reasoning) Z.ai
89.4%
6 GPT-5.2 (xhigh) OpenAI
88.9%
7 gpt-oss-120b (high) OpenAI
87.8%
8 Claude Opus 4.5 (Reasoning) Anthropic
87.1%
9 MiMo-V2-Flash (Reasoning) Xiaomi
86.8%
10 GPT-5.1 (high) OpenAI
86.8%
11 DeepSeek V3.2 (Reasoning) DeepSeek
86.2%
12 OpenAI: o4 Mini High OpenAI
85.9%
13 Gemini 3 Pro Preview (low) Google
85.7%
14 MoonshotAI: Kimi K2 Thinking Moonshot AI
85.3%
15 GPT-5.1 Codex (high) OpenAI
84.9%
16 GPT-5 (high) OpenAI
84.6%
17 GPT-5 Codex (high) OpenAI
84.0%
18 GPT-5 mini (high) OpenAI
83.8%
19 GPT-5.1 Codex mini (high) OpenAI
83.6%
20 grok-4-fast-reasoning SpaceXAI
83.2%
21 MiniMax: MiniMax M2 MiniMax
82.6%
22 grok-4-1-fast-reasoning SpaceXAI
82.2%
23 Grok 4 SpaceXAI
81.9%
24 ERNIE 5.0 Thinking Preview Baidu
81.2%
25 MiniMax: MiniMax M2.1Historical MiniMax
81.0%
26 OpenAI: o3 OpenAI
80.8%
27 Apriel-v1.6-15B-Thinker ServiceNow
80.7%
28 Google: Gemini 2.5 ProRetiring Google
80.1%
29 DeepSeek V3.1 Terminus (Reasoning) DeepSeek
79.8%
30 Gemini 3 Flash Preview (Non-reasoning) Google
79.7%
31 DeepSeek V3.2 Exp (Reasoning) DeepSeek
78.9%
32 GPT-5 nano (high) OpenAI
78.9%
33 Qwen3 235B A22B 2507 (Reasoning) Alibaba
78.8%
34 Qwen3 Next 80B A3B (Reasoning) Alibaba
78.4%
35 DeepSeek V3.1 (Reasoning) DeepSeek
78.4%
36 Gemini 2.5 Pro Preview (Mar' 25) Google
77.8%
37 gpt-oss-20b (high) OpenAI
77.7%
38 intellect-3 Prime Intellect
77.7%
39 Gemini 2.5 Pro Preview (May' 25) Google
77.0%
40 DeepSeek R1 0528 (May '25) DeepSeek
77.0%
41 K-EXAONE (Reasoning) LG AI Research
76.8%
42 Qwen: Qwen3 MaxHistorical Alibaba
76.7%
43 Doubao Seed Code ByteDance Seed
76.6%
44 Seed-OSS-36B-Instruct ByteDance Seed
76.5%
45 GPT-5 nano (medium) OpenAI
76.3%
46 GPT-5 (low) OpenAI
76.3%
47 Magistral Medium 1.2 Mistral AI
75.0%
48 EXAONE 4.0 32B (Reasoning) LG AI Research
74.7%
49 KAT-Coder-Pro V1 Kwaipilot
74.7%
50 NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) NVIDIA
74.1%

Access this data

JSON GET /api/v1 
[
  {
    "rank": 1,
    "model": "Gemini 3 Pro Preview (high)",
    "provider": "Google",
    "score": "91.7"
  },
  {
    "rank": 2,
    "model": "Gemini 3 Flash Preview (Reasoning)",
    "provider": "Google",
    "score": "90.8"
  },
  {
    "rank": 3,
    "model": "DeepSeek V3.2 Speciale",
    "provider": "DeepSeek",
    "score": "89.6"
  }
]
Curl 
$ curl -s https://rightrank.ai/api/v1/rankings/livecodebench.json | jq '.[:3]'
CLI brew install rightrank 
$ rightrank top livecodebench --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category livecodebench
$ rightrank value livecodebench  # best performance per dollar
Claude Code Skill Skill 
# In Claude Code, use the RightRank skill:
/rightrank best model for livecodebench
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on livecodebench