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

Gemini 1.5 Pro vs Qwen2.5 Instruct 72B

GooglevsAlibaba34 shared benchmarks248 head-to-head
BenchmarkGemini 1.5 ProQwen2.5 Instruct 72B
AA Intelligence1010
aider_polyglot16.97.6
AIR-Bench 202482.859
anthropic_red_team99.999.6
Arena Hard85.381.2
Artificial Analysis Coding Index23.611.9
bbh89.279.8
bbq94.595.4
Chinese SimpleQA (C-SimpleQA)59.452.2
DROP74.976.7
DROP (F1)89.285
Fortress53.956.4
GPQA Diamond59.149.1
GSM8K95.295.8
harmbench79.972.8
hellaswag93.384.8
HLE4.94.2
humaneval86.686.6
ifeval89.487.2
IFEval (avg)89.487.2
LiveCodeBench30.555.5
MATH9288.4
MBPP+ (EvalPlus-augmented)75.477
mgsm87.587.3
mmlu86.886.1
MMLU-Pro75.871.6
narrativeqa78.374.5
naturalquestions_closedbook45.535.9
OpenBookQA95.296.2
scicode29.526.7
simple_safety_tests97.5100
simpleqa23.410.3
SWE-bench Verified34.223.8
xstest98.897.9

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.