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

GPT-4o mini vs Llama 3.1 Instruct 405B

OpenAIvsMeta29 shared benchmarks622 head-to-head
BenchmarkGPT-4o miniLlama 3.1 Instruct 405B
AA Agentic Index16.3
AA Intelligence78.5
aider_polyglot3.65.8
AIR-Bench 202456.358.6
anthropic_red_team98.396.5
Artificial Analysis Coding Index11.414.5
bbq88.294.5
DROP79.784.8
Fortress48.120.6
gdpval00
GPQA Diamond42.651.5
GSM8K84.396.8
harmbench84.962.7
HLE4.24.2
humaneval87.289
IFBench3139
LiveCodeBench35.530.1
MATH80.282.7
mgsm8791.6
mmlu81.888.6
narrativeqa76.874.9
naturalquestions_closedbook38.545.6
OpenBookQA9294
scicode22.929.9
simple_safety_tests97.898.8
simplebench10.723
simpleqa9.923.2
SWE-bench Verified8.724.5
xstest9695.9

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.