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 3.7 Sonnet vs Llama 3.1 Instruct 405B

AnthropicvsMeta28 shared benchmarks271 head-to-head
BenchmarkClaude 3.7 SonnetLlama 3.1 Instruct 405B
AA Agentic Index376.3
AA Intelligence27.68.5
AA-LCR62.324.7
AA-Omniscience-0.7-17.1
aider_polyglot64.95.8
AIR-Bench 202481.858.6
anthropic_red_team99.796.5
Artificial Analysis Coding Index36.414.5
bbq92.194.5
critpt0.90
Fortress3820.6
gdpval27.40
GPQA Diamond84.851.5
harmbench84.362.7
HLE9.74.2
IFBench48.339
ifeval93.288.6
math_500_em96.273.8
mmmlu86.173.8
OmniScience Accuracy28.223.2
OmniScience Non-Hallucination6049
scicode40.329.9
simple_safety_tests10098.8
simplebench46.423
SWE-bench Verified70.324.5
Terminal-Bench Hard21.26.8
xstest96.495.9
τ²-Bench Telecom (AA run)54.719

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.