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 o1

DeepSeekvsOpenAI40 shared benchmarks534 head-to-head
BenchmarkDeepSeek-V3o1
AA Agentic Index1.631.1
AA Intelligence15.424
AA-LCR41.363.3
AA-Omniscience-37.6-10.6
aider_polyglot55.161.7
AIME 202459.479.2
AIME 202551.381.7
AIR-Bench 202440.880
anthropic_red_team97.198.3
Artificial Analysis Coding Index2339.7
bbq96.797.3
Codeforces11342061
Codeforces (Percentile)58.796.6
Codeforces (Rating)11342061
critpt00.3
DROP (3-shot F1)91.690.2
gdpval011.5
GPQA Diamond68.475.7
GSM8K96.797.1
harmbench49.796.3
HLE5.27.7
humaneval92.188.1
IFBench4170.3
livebench72.452.3
livecodebench_pass1cot40.563.4
MATH91.296.4
math_500_em9496.4
mgsm79.890.8
mmlu89.491.8
mmmlu79.487.7
OmniScience Accuracy25.434.7
OmniScience Non-Hallucination23.330.7
scicode35.835.8
simple_safety_tests95.399
simplebench27.241.7
simpleqa27.747
SWE-bench Verified4248.9
Terminal-Bench Hard15.212.9
xstest97.197
τ²-Bench Telecom (AA run)47.162.6

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.