AI Model Intelligence Platform
← Benchmarks

Best AI Models for Coding Benchmark

Ranking of AI models by Coding benchmark score.

RankModelProviderScoreDatasetVersionDate
1Claude 3.5 SonnetAnthropic92humanevalofficial-20242024-06-20
2Mistral Large 2Mistral92humanevalofficial-20242024-07-24
3GPT-4oOpenAI90.2humanevalofficial-20242024-05-13
4Llama 3.1 405BMeta89humanevalofficial-20242024-07-23
5Llama 3.3 70BMeta88.4humanevalofficial-20242024-12-06
6GPT-4o miniOpenAI87humanevalofficial-20242024-07-18
7Qwen2.5 72BAlibaba85.9humanevalofficial-20242024-09-19
8Claude 3 OpusAnthropic84.9humanevalofficial-20242024-03-04
9Gemini 1.5 ProGoogle84.1humanevaltechreport-20242024-05-14
10DeepSeek V3DeepSeek82.6humanevalpaper-20242024-12-26
11GLM-4Zhipu80.1humanevalofficial-20242024-01-16
12Claude 3 HaikuAnthropic75.9humanevalofficial-20242024-03-04
13Gemini 1.5 FlashGoogle71.7humanevaltechreport-20242024-05-14

Source

Dataset
humaneval
Version
official-2024
Date
2024-06-20

Benchmark

Related Resources

LeaderboardRelated RankingBenchmarksBenchmarks
Featured Models
Claude 3.5 Sonnet (92) →Mistral Large 2 (92) →GPT-4o (90.2) →
Use Cases
Coding →