Gemma 3 1B Instruct vs Llama 3.2 3B Instruct
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Llama 3.2 3B Instruct is the stronger all-rounder.
Scores updated · 22 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- FactsGetting facts right instead of making them up02Llama 3.2 3B Instruct2 of 2 tests
- ReasoningHard problems that need careful thinking01Llama 3.2 3B Instruct1 of 2 tests · 1 tie
- CodingWriting and fixing software01Llama 3.2 3B Instruct1 of 1 test
- Long documentsFinding answers in very long texts01Llama 3.2 3B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3.2 3B Instruct1 of 1 test
Coding, long documents and following instructions rest on a single test each.
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 Llama 3.2 3B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+24.8points ahead
- Recent programming contest problemsLiveCodeBench v6+7.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+6.3points ahead
Where Gemma 3 1B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3.2 3B Instruct
- LiveCodeBench v6Llama 3.2 3B Instruct by 7.24.311.5+7.2
ReasoningLlama 3.2 3B Instruct
- GPQA DiamondLlama 3.2 3B Instruct by 1.823.725.5+1.8
- Humanity's Last Examtie5.35.3tie
FactsLlama 3.2 3B Instruct
- AA-Omniscience · Non-hallucinationLlama 3.2 3B Instruct by 24.817.742.5+24.8
- AA-Omniscience · AccuracyLlama 3.2 3B Instruct by 2.53.86.3+2.5
Long documentsLlama 3.2 3B Instruct
- AA-LCRLlama 3.2 3B Instruct by 4.304.3+4.3
Following instructionsLlama 3.2 3B Instruct
- IFBenchLlama 3.2 3B Instruct by 6.319.926.2+6.3
Other results15 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.
- AA-OmniscienceLlama 3.2 3B Instruct by 27.9-75.5-47.5+27.9
- MMLULlama 3.2 3B Instruct by 20.340.160.4+20.3
- MMLU-ProLlama 3.2 3B Instruct by 20.314.735+20.3
- GSM8KLlama 3.2 3B Instruct by 14.962.877.7+14.9
- MGSMLlama 3.2 3B Instruct by 14.643.658.2+14.6
- HumanEvalGemma 3 1B Instruct by 13.541.528+13.5
- MBPPLlama 3.2 3B Instruct by 13.535.248.7+13.5
- MMMLULlama 3.2 3B Instruct by 13.534.447.9+13.5
- HumanEval+Gemma 3 1B Instruct by 13.137.224.1+13.1
- τ²-Bench Telecom (AA run)Llama 3.2 3B Instruct by 10.610.521.1+10.6
- BBHLlama 3.2 3B Instruct by 7.739.146.8+7.7
- LCB v5Llama 3.2 3B Instruct by 7.14.411.5+7.1
- MATH-500 (EM)Gemma 3 1B Instruct by 445.241.2+4
- IFEvalGemma 3 1B Instruct by 2.880.277.4+2.8
- AA Intelligencetie4.85.7tie
Questions people ask
Which is better, Gemma 3 1B Instruct or Llama 3.2 3B Instruct?
Llama 3.2 3B Instruct wins all five areas where both have results: coding, reasoning, facts, long documents and following instructions. Gemma 3 1B Instruct wins none.
Which is better for coding?
Llama 3.2 3B Instruct. It wins the one coding test both models report.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.