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 3.5 Sonnet vs o4-mini

AnthropicvsOpenAI26 shared benchmarks718 head-to-head
BenchmarkClaude 3.5 Sonneto4-mini
AA Intelligence1026.1
aider_polyglot45.372
AIME 20257.492.7
AIR-Bench 202485.978.5
anthropic_red_team99.898.2
arena_vision11461201
Artificial Analysis Coding Index30.225.6
bbq94.994
Fortress1321.5
frontiermath_tier_406.3
GPQA Diamond67.281.4
GSM8K96.90
harmbench98.197
HLE3.916.5
LiveCodeBench32.884.5
MathVista67.784.3
MMMU7281.6
MMMU-Pro54.769.2
scicode36.646.5
SEAL VISTA38.751.8
simple_safety_tests100100
simplebench41.438.7
SWE-bench Verified50.868.1
TAU-bench (airline)4649.2
TAU-bench (retail)69.271.8
xstest95.697.4

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.