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 4.8 vs Llama 3.1 Instruct 405B

AnthropicvsMeta20 shared benchmarks191 head-to-head
BenchmarkClaude Opus 4.8Llama 3.1 Instruct 405B
AA Agentic Index49.46.3
AA Intelligence57.38.5
AA-LCR7324.7
AA-Omniscience28.8-17.1
Artificial Analysis Coding Index74.314.5
critpt20.90
Fortress18.220.6
gdpval54.20
GPQA Diamond93.651.5
HLE57.94.2
IFBench62.239
longbench_v269.136.1
OmniScience Accuracy48.823.2
OmniScience Non-Hallucination60.749
scicode53.529.9
simplebench64.823
SWE-bench Pro69.211.2
SWE-bench Verified88.624.5
Terminal-Bench Hard58.36.8
τ²-Bench Telecom (AA run)94.419

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.