LFM2.5-1.2B-Thinking vs Llama 3.2 Instruct 1B
Wins 3 of 5 areas
Coding · Reasoning · Following instructions
Wins 2 of 5 areas
Facts · Long documents
LFM2.5-1.2B-Thinking is the stronger all-rounder.Llama 3.2 Instruct 1B is better at facts.
Scores updated · 18 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.
- ReasoningHard problems that need careful thinking10LFM2.5-1.2B-Thinking1 of 3 tests · 2 ties
- CodingWriting and fixing software10LFM2.5-1.2B-Thinking1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10LFM2.5-1.2B-Thinking1 of 1 test
- FactsGetting facts right instead of making them up01Llama 3.2 Instruct 1B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Llama 3.2 Instruct 1B1 of 1 test
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 LFM2.5-1.2B-Thinking pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+19points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+14.3points ahead
- Code for real scientific research problemsSciCode+2.5points ahead
Where Llama 3.2 Instruct 1B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+28.1points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLFM2.5-1.2B-Thinking
- SciCodeLFM2.5-1.2B-Thinking by 2.54.21.7+2.5
- Terminal-Bench Hardtie00tie
ReasoningLFM2.5-1.2B-Thinking
- GPQA DiamondLFM2.5-1.2B-Thinking by 14.333.919.6+14.3
- Humanity's Last Examtie6.25.5tie
- CritPttie00tie
FactsLlama 3.2 Instruct 1B
- AA-Omniscience · Non-hallucinationLlama 3.2 Instruct 1B by 28.15.633.7+28.1
- AA-Omniscience · Accuracytie7.47tie
Long documentsLlama 3.2 Instruct 1B
- AA-LCRLlama 3.2 Instruct 1B by 6.706.7+6.7
Following instructionsLFM2.5-1.2B-Thinking
- IFBenchLFM2.5-1.2B-Thinking by 1941.822.8+19
Other results9 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)LFM2.5-1.2B-Thinking by 64.68823.4+64.6
- GSM8KLFM2.5-1.2B-Thinking by 49.985.635.7+49.9
- IFEvalLFM2.5-1.2B-Thinking by 3688.452.4+36
- BFCL v3LFM2.5-1.2B-Thinking by 35.65721.4+35.6
- MMLU-ProLFM2.5-1.2B-Thinking by 28.949.620.8+28.9
- AA-OmniscienceLlama 3.2 Instruct 1B by 25.2-80-54.7+25.2
- τ²-Bench Telecom (AA run)LFM2.5-1.2B-Thinking by 19.619.60+19.6
- AA Agentic IndexLFM2.5-1.2B-Thinking by 6.56.50+6.5
- AA Intelligencetie5.24.8tie
Questions people ask
Which is better, LFM2.5-1.2B-Thinking or Llama 3.2 Instruct 1B?
LFM2.5-1.2B-Thinking wins three of the five areas where both have results: coding, reasoning and following instructions. Llama 3.2 Instruct 1B wins facts and long documents.
Which is better for coding?
LFM2.5-1.2B-Thinking. It wins 1 of the 2 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 18 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.