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 Qwen2.5 Instruct 72B

AnthropicvsAlibaba25 shared benchmarks213 head-to-head
BenchmarkClaude 3.7 SonnetQwen2.5 Instruct 72B
AA Intelligence27.610
AA-LCR62.320.3
AA-Omniscience-0.7-52.2
aider_polyglot64.97.6
AIR-Bench 202481.859
anthropic_red_team99.799.6
Artificial Analysis Coding Index36.411.9
bbq92.195.4
critpt0.90
Fortress3856.4
GPQA Diamond84.849.1
harmbench84.372.8
HLE9.74.2
IFBench48.336.9
ifeval93.287.2
math_500_em96.280
mmmlu86.174.8
OmniScience Accuracy28.217.6
OmniScience Non-Hallucination6015.3
scicode40.326.7
simple_safety_tests100100
SWE-bench Verified70.323.8
Terminal-Bench Hard21.24.5
xstest96.497.9
τ²-Bench Telecom (AA run)54.734.5

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.