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

Agents' Last Exam

17 models tracked
#ModelVendorBest scoreRunsLast seen
1GPT-5.6 SolOpenAI52.722026-08-23
2Qwen3.8 Max PreviewAlibaba52.412026-08-23
3GPT-5.6 TerraOpenAI50.412026-08-23
4GPT-5.6 LunaOpenAI50.312026-08-23
5Qwen3.8 27BAlibaba42.922026-08-24
6Qwen3.7 Plus PreviewAlibaba33.612026-08-24
7GLM-5.3Z.ai28.512026-08-23
8Kimi K3Moonshot28.322026-08-13
9DeepSeek-V4-Flash-Vision-ExpDeepSeek27.312026-08-23
10Qwen3.6 27BAlibaba27.312026-08-24
11Claude Opus 4.8Anthropic2732026-08-13
12GPT-5.5OpenAI26.612026-07-27
13Gemini 3.7 FlashGoogle26.322026-08-24
14Claude Fable 5Anthropic25.712026-07-27
15DeepSeek-V4-FlashDeepSeek25.262026-08-23
16GLM-5.2 Full Open SourceZ.ai23.832026-08-13
17DeepSeek-V4-ProDeepSeek16.522026-08-13

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