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 Sonnet 4.6 vs o3

AnthropicvsOpenAI25 shared benchmarks214 head-to-head
BenchmarkClaude Sonnet 4.6o3
AA Agentic Index61.636.1
AA Intelligence48.431.1
AA-LCR7473.3
AA-Omniscience12.2-15.3
arc_agi_186.560.8
ARC-AGI-260.46.5
arena_vision12781217
Artificial Analysis Coding Index6338.4
browsecomp76.249.7
critpt3.11.1
frontiermath_tier_48.32.1
gdpval54.812.8
GPQA Diamond89.983.3
harmbench24.298.4
HLE4920.3
IFBench56.671.4
MMMU-Pro75.676.4
OmniScience Accuracy40.938.6
OmniScience Non-Hallucination51.612.9
scicode4741
simpleqa_verified2953
SWE-bench Verified79.669.1
Tau2 retail91.780.2
Terminal-Bench Hard59.137.1
τ²-Bench Telecom (AA run)97.980.7

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.