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

DeepSeek-V4-Pro vs Qwen3.6 35B A3B

DeepSeekvsAlibaba33 shared benchmarks312 head-to-head
BenchmarkDeepSeek-V4-ProQwen3.6 35B A3B
AA Agentic Index63.321.6
AA Intelligence5332.1
AA-LCR7066.7
AA-Omniscience-10.6-22.2
aime_202696.792.7
Artificial Analysis Coding Index59.441.9
browsecomp83.448.7
critpt130.3
gdpval4927.8
GDPval-AA v213071015
GPQA Diamond90.586
HLE48.222.2
hmmt_feb_202695.283.6
hmmt_nov_202594.489.1
IFBench76.564.4
imo_answer_bench89.878.9
MCP Atlas74.262.8
MMLU-Pro87.585.6
nl2repo38.529.4
OmniScience Accuracy4318.8
OmniScience Non-Hallucination12.249.5
scicode5035.8
SWE-bench Multilingual76.267.2
SWE-bench Pro55.449.5
SWE-bench Verified80.673.4
TauBench V3 - Banking30.19.3
Terminal-Bench 2.067.951.5
Terminal-Bench 2.172.144.9
Terminal-Bench Hard46.234.8
tool_decathlon52.826.9
toolathlon51.826.9
τ²-Bench Telecom (AA run)96.295.3
τ³-Bench25.867.2

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.