Granite 4.0 H 1B vs LFM2.5-1.2B-Instruct
Wins 2 of 6 areas
Coding · Long documents
Wins 2 of 6 areas
Reasoning · Following instructions
The two are evenly matched.Granite 4.0 H 1B is better at coding and long documents; LFM2.5-1.2B-Instruct at reasoning and following instructions.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking02LFM2.5-1.2B-Instruct2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01LFM2.5-1.2B-Instruct1 of 1 test
- CodingWriting and fixing software10Granite 4.0 H 1B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Granite 4.0 H 1B1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Agents, long documents and following instructions rest on a single test each.
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-Instruct pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.8points ahead
Where Granite 4.0 H 1B pulls ahead
- Code for real scientific research problemsSciCode+5.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+3.4points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGranite 4.0 H 1B
- SciCodeGranite 4.0 H 1B by 5.98.22.3+5.9
- Terminal-Bench Hardtie00tie
ReasoningLFM2.5-1.2B-Instruct
- GPQA DiamondLFM2.5-1.2B-Instruct by 6.326.332.6+6.3
- Humanity's Last ExamLFM2.5-1.2B-Instruct by 1.756.7+1.7
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.0 H 1B by 3.418.314.9+3.4
- AA-Omniscience · AccuracyLFM2.5-1.2B-Instruct by 1.85.27+1.8
Following instructionsLFM2.5-1.2B-Instruct
- IFBenchLFM2.5-1.2B-Instruct by 17.626.243.8+17.6
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.
- GSM8KGranite 4.0 H 1B by 65.369.64.3+65.3
- MATH-500 (EM)Granite 4.0 H 1B by 41.447.25.8+41.4
- MMLU-ProLFM2.5-1.2B-Instruct by 16.827.644.4+16.8
- τ²-Bench Telecom (AA run)Granite 4.0 H 1B by 8.819.610.8+8.8
- IFEvalLFM2.5-1.2B-Instruct by 6.180.186.2+6.1
- AA Agentic IndexGranite 4.0 H 1B by 2.96.53.6+2.9
- BFCL v3Granite 4.0 H 1B by 1.650.749.1+1.6
- AA-Omnisciencetie-72.3-72.1tie
- AA Intelligencetie5.25.2tie
Questions people ask
Which is better, Granite 4.0 H 1B or LFM2.5-1.2B-Instruct?
Granite 4.0 H 1B and LFM2.5-1.2B-Instruct each win two of the six areas where both have results. Granite 4.0 H 1B wins coding and long documents; LFM2.5-1.2B-Instruct wins reasoning and following instructions. They are level on agents and facts.
Which is better for coding?
Granite 4.0 H 1B. It wins 1 of the 2 coding tests both models report; LFM2.5-1.2B-Instruct wins none, and 1 is a tie.
How do you compare the two?
We use the 19 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 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.