VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

HumanEval-Mul (Pass@1)

7 models tracked

HumanEval-Mul (multilingual HumanEval extension) — Distinct multilingual-code extension of HumanEval, not the same benchmark as base HumanEval.

#ModelVendorBest scoreRunsLast seen
1DeepSeek-V3DeepSeek82.622026-08-23
2Claude 3.5 SonnetAnthropic81.712026-05-03
3GPT-4oOpenAI80.512026-05-03
4DeepSeek-V2.5DeepSeek77.422026-08-23
5Qwen2.5 Instruct 72BAlibaba77.312026-05-03
6Llama 3.1 Instruct 405BMeta77.212026-05-03
7DeepSeek-V2DeepSeek69.312026-05-03

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.