Llama 3.2 Instruct 1B vs Qwen3 1.7B
Wins 1 of 5 areas
Long documents
Wins 3 of 5 areas
Coding · Reasoning · Following instructions
Qwen3 1.7B is the stronger all-rounder.Llama 3.2 Instruct 1B is better at long documents.
Scores updated · 24 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.
- CodingWriting and fixing software02Qwen3 1.7B2 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking01Qwen3 1.7B1 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01Qwen3 1.7B1 of 1 test
- Long documentsFinding answers in very long texts10Llama 3.2 Instruct 1B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 Qwen3 1.7B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+20points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+4.1points ahead
Where Llama 3.2 Instruct 1B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+28.5points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 1.7B
- LiveCodeBench v6Qwen3 1.7B by 204.124.1+20
- SciCodeQwen3 1.7B by 2.61.74.3+2.6
- Terminal-Bench Hardtie00tie
ReasoningQwen3 1.7B
- GPQA DiamondQwen3 1.7B by 1619.635.6+16
- Humanity's Last Examtie5.54.6tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationLlama 3.2 Instruct 1B by 28.533.75.2+28.5
- AA-Omniscience · AccuracyQwen3 1.7B by 1.978.9+1.9
Long documentsLlama 3.2 Instruct 1B
- AA-LCRLlama 3.2 Instruct 1B by 6.76.70+6.7
Following instructionsQwen3 1.7B
- IFBenchQwen3 1.7B by 4.122.826.9+4.1
Other results14 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.
- MATH-500 (EM)Qwen3 1.7B by 58.523.481.9+58.5
- HumanEval+Qwen3 1.7B by 37.823.261+37.8
- MGSMQwen3 1.7B by 37.529.166.6+37.5
- MMLU-ProQwen3 1.7B by 36.220.857+36.2
- BFCL v3Qwen3 1.7B by 3421.455.4+34
- τ²-Bench Telecom (AA run)Qwen3 1.7B by 26026+26
- LCB v5Qwen3 1.7B by 22.93.626.5+22.9
- AA-OmniscienceLlama 3.2 Instruct 1B by 22.8-54.7-77.5+22.8
- IFEvalQwen3 1.7B by 21.652.474+21.6
- GSM8KQwen3 1.7B by 15.735.751.4+15.7
- MMLUQwen3 1.7B by 12.546.659.1+12.5
- AA Agentic IndexQwen3 1.7B by 8.708.7+8.7
- MMMLUQwen3 1.7B by 8.338.146.5+8.3
- AA Intelligencetie4.85.2tie
Questions people ask
Which is better, Llama 3.2 Instruct 1B or Qwen3 1.7B?
Qwen3 1.7B wins three of the five areas where both have results: coding, reasoning and following instructions. Llama 3.2 Instruct 1B wins long documents. They are level on facts.
Which is better for coding?
Qwen3 1.7B. It wins 2 of the 3 coding tests both models report; Llama 3.2 Instruct 1B wins none, and 1 is a tie.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.