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 Llama 3.1 Instruct 405B

AnthropicvsMeta20 shared benchmarks191 head-to-head
BenchmarkClaude Opus 4.7Llama 3.1 Instruct 405B
AA Agentic Index64.66.3
AA Intelligence558.5
AA-LCR75.324.7
AA-Omniscience27.3-17.1
Artificial Analysis Coding Index73.614.5
critpt120
gdpval58.60
GPQA Diamond94.251.5
harmbench17.562.7
HLE54.74.2
IFBench58.639
mmmlu91.573.8
OmniScience Accuracy48.923.2
OmniScience Non-Hallucination57.749
scicode54.529.9
simplebench61.723
SWE-bench Pro64.311.2
SWE-bench Verified87.624.5
Terminal-Bench Hard54.56.8
τ²-Bench Telecom (AA run)88.619

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.