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-V3 vs Qwen3.5 397B A17B

DeepSeekvsAlibaba32 shared benchmarks230 head-to-head
BenchmarkDeepSeek-V3Qwen3.5 397B A17B
AA Agentic Index1.653.3
AA Intelligence15.434.3
AA-LCR41.372.7
AA-Omniscience-37.6-30.8
Artificial Analysis Coding Index2348.2
C-Eval90.193
critpt01.7
gdpval035.8
GPQA Diamond68.489.3
GSM8K96.766.7
HLE5.229
HMMT 202527.592.7
hmmt_feb_202529.294.8
IFBench4178.8
ifeval87.392.6
LiveCodeBench v646.983.6
longbench_v248.763.2
mmlu_prox70.584.7
mmlu_redux90.594.9
MMLU-Pro81.287.8
mmmlu79.488.5
multichallenge31.467.6
OmniScience Accuracy25.430.8
OmniScience Non-Hallucination23.317.3
scicode35.842
supergpqa53.770.4
SWE-bench Verified4276.4
TauBench V3 - Banking4.713.4
Terminal-Bench 2.116.951.3
Terminal-Bench Hard15.240.9
τ²-Bench Telecom (AA run)47.195.6
τ³-Bench4.713.4

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.