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

Program Bench

11 models tracked

Program Bench / ProgramBench — Programming eval in GLM-5.2/Kimi-K2 cards; folds spelling variant. Distinct from PostTrainBench.

#ModelVendorBest scoreRunsLast seen
1Kimi K3Moonshot77.832026-08-23
2GPT-5.6 SolOpenAI77.612026-07-27
3Claude Fable 5Anthropic76.812026-07-27
4Claude Opus 4.8Anthropic71.942026-07-27
5GPT-5.5OpenAI70.842026-07-27
6GLM-5.2 Full Open SourceZ.ai63.752026-08-23
7Kimi K2.7 CodeMoonshot53.622026-08-23
8GLM-5.1Z.ai50.922026-07-13
9DeepSeek-V4-ProDeepSeek47.822026-07-13
10Gemini 3.1 ProGoogle39.522026-07-13
11GLM-5.3Z.ai1912026-08-23

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