Grok 2 is the stronger all-rounder.
Scores updated · 9 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Grok 2 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.1points ahead
- Code for real scientific research problemsSciCode+12.1points ahead
- College exam questions with charts, maps and diagramsMMMU+6.5points ahead
Where Gemma 3 12B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.1points ahead
Every test, side by side
All 9 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA DiamondGrok 2 by 16.134.951+16.1
- Humanity's Last ExamGemma 3 12B by 1.14.23.1+1.1
Images and chartsGrok 2
Other results4 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- MMLU-ProGrok 2 by 14.960.675.5+14.9
- DocVQAGrok 2 by 6.587.193.6+6.5
- AA IntelligenceGrok 2 by 3.33.87.1+3.3
- HumanEvalGrok 2 by 385.488.4+3
Questions people ask
Which is better, Gemma 3 12B or Grok 2?
Grok 2 wins two of the three areas where both have results: coding and images and charts. Gemma 3 12B wins none. They are level on reasoning.
Which is better for coding?
Grok 2. It wins the one coding test both models report.
How do you compare the two?
We use the 9 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.