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 o4-mini

AnthropicvsOpenAI38 shared benchmarks2116 head-to-head
BenchmarkClaude 3.7 Sonneto4-mini
AA Agentic Index3736.1
AA Intelligence27.626.1
AA-LCR62.360
AA-Omniscience-0.7-35.7
aider_polyglot64.972
AIME 202554.892.7
AIR-Bench 202481.878.5
anthropic_red_team99.798.2
arc_agi_113.658.7
ARC-AGI-206.1
arena_vision11951201
Artificial Analysis Coding Index36.425.6
bbq92.194
critpt0.90.6
Fortress3821.5
gdpval27.425.4
GPQA Diamond84.881.4
harmbench84.397
HLE9.716.5
IFBench48.368.7
MMMU7581.6
MMMU-Pro60.169.2
multichallenge51.644.9
MultiNRC27.822.2
OmniScience Accuracy28.224.8
OmniScience Non-Hallucination6019.5
scicode40.346.5
SEAL VISTA48.251.8
simple_safety_tests100100
simplebench46.438.7
swe_bench_bash52.845
SWE-bench Verified70.368.1
TAU-bench (airline)58.449.2
TAU-bench (retail)81.271.8
Terminal-Bench Hard21.215.2
usamo_20253.619.1
xstest96.497.4
τ²-Bench Telecom (AA run)54.755.6

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.