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 Opus 4.7 vs o3

AnthropicvsOpenAI25 shared benchmarks223 head-to-head
BenchmarkClaude Opus 4.7o3
AA Agentic Index64.636.1
AA Intelligence5531.1
AA-LCR75.373.3
AA-Omniscience27.3-15.3
arc_agi_19260.8
ARC-AGI-275.86.5
arena_vision13041217
Artificial Analysis Coding Index73.638.4
browsecomp79.849.7
critpt121.1
frontiermath_tier_422.92.1
gdpval58.612.8
GPQA Diamond94.283.3
harmbench17.598.4
HLE54.720.3
IFBench58.671.4
MMMU-Pro78.876.4
OmniScience Accuracy48.938.6
OmniScience Non-Hallucination57.712.9
scicode54.541
simplebench61.753.1
simpleqa_verified50.653
SWE-bench Verified87.669.1
Terminal-Bench Hard54.537.1
τ²-Bench Telecom (AA run)88.680.7

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.