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 4.6 vs GPT-4o

AnthropicvsOpenAI45 shared benchmarks387 head-to-head
BenchmarkClaude Opus 4.6GPT-4o
AA Agentic Index67.69.7
AA Intelligence44.911.2
AA-LCR74.355
AA-Omniscience13.7-10.5
AIME 202599.811.7
arc_agi_1934.5
ARC-AGI-268.80
arena_vision13001162
Artificial Analysis Coding Index48.124.2
Chinese SimpleQA (C-SimpleQA)76.464.6
critpt12.60
ERQA40.835.2
Fortress20.547.2
gdpval55.90
GPQA Diamond91.370.1
GSM8K0.695.6
HLE53.15.3
IFBench62.536
LiveCodeBench88.838.3
LiveCodeBench v688.830.9
mathvision71.230.4
metr_hcast7725
metr_re_bench97.40
metr_swaa98.599.2
MMLU-Pro89.174.7
mmmlu91.181.4
MMMU-Pro77.359.9
multichallenge5640.3
MultiNRC57.112.4
OmniScience Accuracy4723.7
OmniScience Non-Hallucination37.262.1
OSWorld-Verified72.75
RealWorldQA73.975.4
scicode5233.4
SEAL VISTA46.134.9
simplebench67.617.8
swe_bench_bash75.621.6
SWE-bench Verified80.838.8
Tau2 retail91.963.4
Terminal-Bench Hard65.48.3
vectara_answer_rate99.893.8
vectara_avg_summary_length137.686.6
vectara_factual_consistency87.890.4
vectara_hallucination_rate12.29.6
τ²-Bench Telecom (AA run)99.328.9

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.