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

Claude 3.7 Sonnet vs GPT-5.2

AnthropicvsOpenAI31 shared benchmarks427 head-to-head
BenchmarkClaude 3.7 SonnetGPT-5.2
AA Agentic Index3760.2
AA Intelligence27.643.3
AA-LCR62.379.3
AA-Omniscience-0.70.3
AIME 202554.8100
arc_agi_113.686.2
ARC-AGI-2052.9
arena_vision11951245
Artificial Analysis Coding Index36.448.7
critpt0.911.6
Fortress3817.5
gdpval27.448.3
GPQA Diamond84.892.4
HLE9.745.5
hmmt_feb_202531.7100
IFBench48.375.4
metr_hcast54.277
metr_re_bench035
metr_swaa98.799.6
mmmlu86.189.6
MMMU-Pro60.179.5
MultiNRC27.842.2
OmniScience Accuracy28.244.3
OmniScience Non-Hallucination6038.4
scicode40.352.1
SEAL VISTA48.246.6
simplebench46.445.8
swe_bench_bash52.872.8
SWE-bench Verified70.380
Terminal-Bench Hard21.262.2
τ²-Bench Telecom (AA run)54.798.7

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.