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 Gemini 3.5 Flash

DeepSeekvsGoogle42 shared benchmarks1130 head-to-head
BenchmarkDeepSeek-V4-ProGemini 3.5 Flash
AA Agentic Index63.370.4
AA Intelligence5352
AA-LCR7081
AA-Omniscience-10.621.2
aime_202696.795
apexAgents24.347.1
arena_elo14571477
arena_text_factuality14501466
Artificial Analysis Coding Index59.470.1
coding_arena_elo15821490
critpt1313.1
DeepSWE12.837
gdpval4957.8
GDPval-AA (Elo)15541656
GDPval-AA v213071357
GPQA Diamond90.592.2
HLE48.242.7
hmmt_feb_202695.295.5
IFBench76.576.3
itbenchSre38.340.3
livebench73.675
livebench_agentic_coding42.649
livebench_coding7078.2
livebench_data_analysis74.564.9
livebench_instruction_following62.475.6
livebench_language78.184.6
livebench_math90.788.2
livebench_reasoning82.782
MCP Atlas74.283.6
OmniScience Accuracy4351.4
OmniScience Non-Hallucination12.238.2
scicode5053.1
simplebench50.976.7
simpleqa_verified57.968.4
SWE-bench Pro55.455.1
TauBench V3 - Banking30.132.2
Terminal-Bench 2.067.976.2
Terminal-Bench 2.172.178.7
Terminal-Bench Hard46.246.2
toolathlon51.856.5
τ²-Bench Telecom (AA run)96.295.6
τ³-Bench25.825.4

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.