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-4o

AnthropicvsOpenAI43 shared benchmarks365 head-to-head
BenchmarkClaude 3.7 SonnetGPT-4o
AA Agentic Index379.7
AA Intelligence27.611.2
AA-LCR62.355
AA-Omniscience-0.7-10.5
aider_polyglot64.930.7
AIME 202554.811.7
AIR-Bench 202481.862.4
anthropic_red_team99.799.1
arc_agi_113.64.5
ARC-AGI-200
arena_vision11951162
Artificial Analysis Coding Index36.424.2
bbq92.195.1
critpt0.90
Fortress3847.2
gdpval27.40
GPQA Diamond84.870.1
harmbench84.382.9
HLE9.75.3
IFBench48.336
ifeval93.284.3
math_500_em96.274.6
metr_hcast54.225
metr_re_bench00
metr_swaa98.799.2
mmmlu86.181.4
MMMU7572.2
MMMU-Pro60.159.9
multichallenge51.640.3
MultiNRC27.812.4
OmniScience Accuracy28.223.7
OmniScience Non-Hallucination6062.1
scicode40.333.4
SEAL VISTA48.234.9
simple_safety_tests10098.5
simplebench46.417.8
swe_bench_bash52.821.6
SWE-bench Verified70.338.8
TAU-bench (airline)58.442.8
TAU-bench (retail)81.260.3
Terminal-Bench Hard21.28.3
xstest96.497.3
τ²-Bench Telecom (AA run)54.728.9

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.