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 Llama 3.1 Instruct 405B

AnthropicvsMeta24 shared benchmarks213 head-to-head
BenchmarkClaude Opus 4.6Llama 3.1 Instruct 405B
AA Agentic Index67.66.3
AA Intelligence44.98.5
AA-LCR74.324.7
AA-Omniscience13.7-17.1
Artificial Analysis Coding Index48.114.5
Chinese SimpleQA (C-SimpleQA)76.454.7
critpt12.60
Fortress20.520.6
gdpval55.90
GPQA Diamond91.351.5
GSM8K0.696.8
HLE53.14.2
IFBench62.539
LiveCodeBench88.830.1
MMLU-Pro89.173.4
mmmlu91.173.8
OmniScience Accuracy4723.2
OmniScience Non-Hallucination37.249
scicode5229.9
simplebench67.623
SWE-bench Pro57.311.2
SWE-bench Verified80.824.5
Terminal-Bench Hard65.46.8
τ²-Bench Telecom (AA run)99.319

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.