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 GPT-4o mini

GooglevsOpenAI40 shared benchmarks346 head-to-head
BenchmarkGemini 1.5 ProGPT-4o mini
AA Intelligence107
AI2D80.975.2
aider_polyglot16.93.6
AIR-Bench 202482.856.3
anthropic_red_team99.998.3
ARC-AGI-20.80
Artificial Analysis Coding Index23.611.4
bbq94.588.2
BLINK6151.9
DROP74.979.7
Fortress53.948.1
GPQA Diamond59.142.6
GSM8K95.284.3
harmbench79.984.9
HLE4.94.2
humaneval86.687.2
InterGPS (test)58.239.9
LiveCodeBench30.535.5
MATH9280.2
MathVista70.656.7
mgsm87.587
MMBench (dev-en)87.983.8
mmlu86.881.8
MMMU68.459.4
MMMU (val) (Pass@1)54.152.1
MMMU-Pro5541.5
narrativeqa78.376.8
naturalquestions_closedbook45.538.5
OpenBookQA95.292
POPE (test)89.383.6
scicode29.522.9
ScienceQA (img-test)8684
simple_safety_tests97.597.8
simplebench27.110.7
simpleqa23.49.9
SWE-bench Verified34.28.7
TextVQA (val)64.570.9
Video-MME78.668.9
Video-MME Overall62.661.2
xstest98.896

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.