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

GPT-4o vs Qwen3.5 397B A17B

OpenAIvsAlibaba34 shared benchmarks331 head-to-head
BenchmarkGPT-4oQwen3.5 397B A17B
AA Agentic Index9.753.3
AA Intelligence11.234.3
AA-LCR5572.7
AA-Omniscience-10.5-30.8
arena_vision11621249
Artificial Analysis Coding Index24.248.2
C-Eval7693
critpt01.7
ERQA35.267.5
gdpval035.8
GPQA Diamond70.189.3
GSM8K95.666.7
HLE5.329
IFBench3678.8
ifeval84.392.6
LiveCodeBench v630.983.6
longbench_v248.163.2
mmlu_prox61.184.7
mmlu_redux8894.9
MMLU-Pro74.787.8
mmmlu81.488.5
MMMU72.285
MMMU-Pro59.979
MMStar63.983.8
multichallenge40.367.6
OmniScience Accuracy23.730.8
OmniScience Non-Hallucination62.117.3
RealWorldQA75.483.9
scicode33.442
supergpqa42.470.4
SWE-bench Verified38.876.4
Terminal-Bench Hard8.340.9
VideoMMMU61.284.7
τ²-Bench Telecom (AA run)28.995.6

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.