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 4 Opus vs o1

AnthropicvsOpenAI34 shared benchmarks249 head-to-head
BenchmarkClaude 4 Opuso1
AA Intelligence31.724
AA-LCR4063.3
aider_polyglot70.761.7
AIME 20247679.2
AIME 202575.581.7
AIR-Bench 202485.780
anthropic_red_team98.998.3
arena_vision12071193
Artificial Analysis Coding Index3439.7
bbq99.397.3
Fortress27.619.4
GPQA Diamond79.675.7
harmbench91.796.3
HLE12.37.7
IFBench53.770.3
livebench74.652.3
math_500_em98.296.4
metr_hcast61.742.6
metr_re_bench200
metr_swaa99.8100
mmlu92.991.8
mmmlu88.887.7
MMMU73.777.6
scicode40.935.8
SEAL VISTA4745.3
simple_safety_tests10099
simplebench58.841.7
simpleqa22.847
SWE-bench Verified79.448.9
TAU-bench (airline)59.650
TAU-bench (retail)81.470.8
Terminal-Bench Hard31.112.9
xstest9797
τ²-Bench Telecom (AA run)73.462.6

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.