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 o4-mini

AnthropicvsOpenAI29 shared benchmarks263 head-to-head
BenchmarkClaude Opus 4.7o4-mini
AA Agentic Index64.636.1
AA Intelligence5526.1
AA-LCR75.360
AA-Omniscience27.3-35.7
arc_agi_19258.7
ARC-AGI-275.86.1
arena_vision13041201
Artificial Analysis Coding Index73.625.6
browsecomp79.851.5
critpt120.6
frontiermath_tier_422.96.3
gdpval58.625.4
GPQA Diamond94.281.4
harmbench17.597
HLE54.716.5
IFBench58.668.7
MMMU-Pro78.869.2
OmniScience Accuracy48.924.8
OmniScience Non-Hallucination57.719.5
scicode54.546.5
simplebench61.738.7
simpleqa_verified50.623.9
SWE-bench Verified87.668.1
Terminal-Bench Hard54.515.2
vectara_answer_rate9899.2
vectara_avg_summary_length149.1130.9
vectara_factual_consistency8881.4
vectara_hallucination_rate1218.6
τ²-Bench Telecom (AA run)88.655.6

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.