VECTOR WIREAI INTELLIGENCE
PKT
Refresh Models Deals Regulatory Sources

Questions this page answers

Which model leads InfoVQA_test?
Across 12 models scored on InfoVQA_test, Kimi K2.5 leads at 92.6, ahead of Qwen3 VL 235B A22B Reasoning at 89.5. The median tracked score is 86, and the field spans 80.3 to 92.6.

InfoVQA_test

Across 12 models scored on InfoVQA_test, Kimi K2.5 leads at 92.6, ahead of Qwen3 VL 235B A22B Reasoning at 89.5. The median tracked score is 86, and the field spans 80.3 to 92.6.

12 models tracked
Data as of August 25, 2026
#ModelVendorBest scoreRunsLast seen
1Kimi K2.5Moonshot92.612026-08-25
2Qwen3 VL 235B A22B ReasoningAlibaba89.512026-08-25
3Qwen3 VL 32B ReasoningAlibaba89.212026-08-25
4Qwen3 VL 235B A22B InstructAlibaba89.212026-08-25
5Qwen3 VL 32B InstructAlibaba8712026-08-25
6Qwen3 VL 30B A3B ReasoningAlibaba8612026-08-25
7Qwen3 VL Thinking (8B)Alibaba8612026-08-25
8Qwen2 VL 72B InstructAlibaba84.522026-08-25
9Qwen3 VL 8B InstructAlibaba83.112026-08-25
10Qwen3 VL 4B (Reasoning)Alibaba8312026-08-25
11Qwen3 VL 30B A3B InstructAlibaba8212026-08-25
12Qwen3 VL 4B InstructAlibaba80.312026-08-25

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