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-Flash vs Gemini 3.5 Flash

DeepSeekvsGoogle42 shared benchmarks932 head-to-head
BenchmarkDeepSeek-V4-FlashGemini 3.5 Flash
AA Agentic Index61.370.4
AA Intelligence51.852
AA-LCR74.381
AA-Omniscience-14.321.2
aime_202695.895
arc_agi_18492.5
ARC-AGI-24672.1
arena_elo14391477
arena_text_factuality14341466
Artificial Analysis Coding Index69.170.1
coding_arena_elo14311490
critpt16.613.1
DeepSWE54.437
gdpval52.957.8
GDPval-AA (Elo)13951656
GDPval-AA v211891357
GPQA Diamond90.892.2
HLE38.642.7
hmmt_feb_202694.895.5
IFBench79.276.3
itbenchSre31.540.3
livebench_agentic_coding46.849
livebench_coding7578.2
livebench_data_analysis79.364.9
livebench_instruction_following65.575.6
livebench_language79.284.6
livebench_math86.888.2
livebench_reasoning86.682
MCP Atlas6983.6
OmniScience Accuracy40.451.4
OmniScience Non-Hallucination15.638.2
scicode49.953.1
simplebench46.376.7
simpleqa_verified4568.4
SWE-bench Pro52.655.1
TauBench V3 - Banking39.432.2
Terminal-Bench 2.056.976.2
Terminal-Bench 2.182.778.7
Terminal-Bench Hard38.646.2
toolathlon70.356.5
τ²-Bench Telecom (AA run)95.695.6
τ³-Bench22.925.4

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.