The Model Index
Up to four models

GPT-4o mini vs Gemma 2

On the index (GPT-4 = 100), GPT-4o mini scores 104 and Gemma 2 100. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-4o mini
Presets
GPT-4o mini
10487–120
WeightsClosed
ReleasedJul 2024
Price in / out$0.15 / $0.60
Context128K
Core tests taken3 of 9
Gemma 2
10084–117
WeightsOpen
ReleasedJun 2024
Price in / out$0.65 / $0.65
Context8K
Core tests taken1 of 9

GPT-4o mini and Gemma 2 are too close to call (3 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 2.5× less.

Test by testthird-party results

GPT-4o miniGemma 2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGPT-4o miniGemma 2
Reasoning & knowledge
GPQA Diamond (Epoch AI)37.7%36.5%
MMLU (HELM runs)76.7%75.7%
Maths
AIME-style maths (OTIS mock)6.9%1.4%
MATH (level 5)52.6%27.9%
Agents
DTBench54.4%48.0%
LMCA10.4%7.1%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG