The AI tools index that doesn't waste your time.不浪费你时间的 AI 工具索引。
Coding · weight 7%代码 · 权重 7%

LiveCodeBench

official site官网 ↗

What it tests: Competitive-programming problems (LeetCode/AtCoder/Codeforces) collected continuously after model training cutoffs, scored by pass rate with zero contamination by design.

考什么:持续从 LeetCode/AtCoder/Codeforces 采集的新竞赛题,题目发布晚于模型训练截止日,从机制上杜绝刷题污染,按通过率计分。

Why it counts: The anti-contamination gold standard for coding — a high score here is much harder to fake than on static benchmarks.

为什么算数:代码领域防污染的标杆——题库月月更新,在这里拿高分比在静态 benchmark 上难作弊得多。

Maintainer维护方CMU + Jina AI 等
License许可MIT
Reference point (prior-gen SOTA)参考点(上一代 SOTA)80
◈

Standings实时排名

45 models with sourced scores 个模型有溯源成绩
#Model模型Score成绩Index指数Dated日期Measured by测评方
1Kimi K3Moonshot AI93.51002026-073rd-party第三方source ↗×4⚠±6.31
2DeepSeek V4 Pro 0423DeepSeek93.5⚡max100—3rd-party第三方source ↗×8
3DeepSeek V4 Flash 0731DeepSeek91.698—3rd-party第三方source ↗
4Qwen3.7 MaxQwen91.698—3rd-party第三方source ↗×4
5DeepSeek V4 Flash 0423DeepSeek91.6⚡max98—3rd-party第三方source ↗×5⚠±26.1
6Qwen3.8 Max PrimeQwen90.397—3rd-party第三方source ↗
7Claude Fable 5Anthropic89.7896—3rd-party第三方source ↗×4⚠±9.48
8Qwen3.7 PlusQwen89.696—3rd-party第三方source ↗×3
9DeepSeek V3.2DeepSeek89.6962026-08-193rd-party第三方source ↗×3⚠±6.3
10Claude Opus 5Anthropic89.03952026-073rd-party第三方source ↗×5⚠±29.63
11Nemotron 3 UltraNVIDIA8995—3rd-party第三方source ↗
12Gemini 3.1 Pro PreviewGoogle88.4895—3rd-party第三方source ↗×6⚠±30.7
13Gemini 3.6 FlashGoogle88.0894—3rd-party第三方source ↗×4⚠±54.58
14Claude Opus 4.8Anthropic87.8294—3rd-party第三方source ↗×3⚠±16.62
15Qwen3.7 FlashQwen87.7942026-073rd-party第三方source ↗×2⚠±14.6
16Gemini 3.5 FlashGoogle87.694—3rd-party第三方source ↗×3⚠±45.21
17GPT-5.6 TerraOpenAI85.992—official官方榜source ↗×4⚠±14.71
18Grok 4.3xAI84.4990—3rd-party第三方source ↗×3⚠±22.19
19Grok 4.20xAI84.2790—3rd-party第三方source ↗
20Kimi K2 ThinkingMoonshot AI83.1⚡high89—3rd-party第三方source ↗×3⚠±19.95
21Claude Sonnet 5Anthropic82.4388—3rd-party第三方source ↗×4⚠±19.23
22MiniMax M3MiniMax82.1588—3rd-party第三方source ↗×4⚠±58
23Kimi K2.7 CodeMoonshot AI82.0588—3rd-party第三方source ↗×3⚠±21.2
24Seed-2.0-LiteByteDance Seed81.7872026-073rd-party第三方source ↗×3⚠±9.8
25GPT-5.6 SolOpenAI81872026-073rd-party第三方source ↗×3⚠±3.2
26GPT-5.5OpenAI80.686—3rd-party第三方source ↗×2⚠±13.2
27MiniMax M2.7MiniMax79.9385—3rd-party第三方source ↗×2
28Grok 4.5xAI79842026-073rd-party第三方source ↗×3⚠±8.35
29Claude Haiku 4.5Anthropic75.03480—3rd-party第三方source ↗×2⚠±23.93
30GPT-5.6 Terra ProOpenAI71.9977—3rd-party第三方source ↗
31gpt-oss-120bOpenAI70.776—3rd-party第三方source ↗×3⚠±13.98
32GLM 5.1Z.ai70.676—3rd-party第三方source ↗×4⚠±18.8
33Gemini 3.1 Flash LiteGoogle69.975—3rd-party第三方source ↗
34GLM 5.2Z.ai69.574—3rd-party第三方source ↗×2
35Step 3.7 FlashStepFun6974—3rd-party第三方source ↗×3⚠±17.4
36GPT-5.6 LunaOpenAI67.3172—3rd-party第三方source ↗×2
37Seed-2.0-MiniByteDance Seed64.1692026-073rd-party第三方source ↗×2
38Mistral Small 4Mistral AI48.252—3rd-party第三方source ↗
39Mistral Medium 3.5Mistral AI44.8448—3rd-party第三方source ↗×2⚠±29
40Llama 4 MaverickMeta43.446—3rd-party第三方source ↗×2
41Mistral LargeMistral AI36.239—3rd-party第三方source ↗×2
42Command ACohere35.0738—3rd-party第三方source ↗×3⚠±50.68
43Llama 4 ScoutMeta33.236—3rd-party第三方source ↗×2
44Nova Premier 1.0Amazon31.734—3rd-party第三方source ↗
45GPT-5.6 Luna ProOpenAI20.622—3rd-party第三方source ↗

How scores become the Intelligence Score →成绩如何合成智能评分 →