The Model Index
Up to four models

Gemma 3 vs Llama 4 Scout

On the index (GPT-4 = 100), Gemma 3 scores 113 and Llama 4 Scout 112. 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 Gemma 3
Presets
Gemma 3
11397–129
WeightsOpen
ReleasedMar 2025
Price in / out$0.080 / $0.45
Context131K
Core tests taken1 of 9
Llama 4 Scout
11296–128
WeightsOpen
ReleasedApr 2025
Price in / out$0.10 / $0.30
Context1.31M
Core tests taken2 of 9

Gemma 3 and Llama 4 Scout are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, at a similar price.

Test by testthird-party results

Gemma 3Llama 4 Scout
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGemma 3Llama 4 Scout
Reasoning & knowledge
GPQA Diamond (Epoch AI)47.7%51.8%
Fiction.LiveBench33.3%36.0%
Maths
AIME-style maths (OTIS mock)22.5%7.8%
MATH (level 5)74.0%62.3%
Agents
DTBench52.5%57.9%
LMCA12.3%12.0%

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

This page as a chartDownload PNG