Granite 4.0 H 1B vs LFM2.5-1.2B-Thinking
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-Thinking 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-Thinking2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01LFM2.5-1.2B-Thinking1 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-Thinking pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.2points ahead
Where Granite 4.0 H 1B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.7points ahead
- Code for real scientific research problemsSciCode+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 48.24.2+4
- Terminal-Bench Hardtie00tie
ReasoningLFM2.5-1.2B-Thinking
- GPQA DiamondLFM2.5-1.2B-Thinking by 7.626.333.9+7.6
- Humanity's Last ExamLFM2.5-1.2B-Thinking by 1.256.2+1.2
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.0 H 1B by 12.718.35.6+12.7
- AA-Omniscience · AccuracyLFM2.5-1.2B-Thinking by 2.25.27.4+2.2
Following instructionsLFM2.5-1.2B-Thinking
- IFBenchLFM2.5-1.2B-Thinking by 15.626.241.8+15.6
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.
- MATH-500 (EM)LFM2.5-1.2B-Thinking by 40.847.288+40.8
- MMLU-ProLFM2.5-1.2B-Thinking by 22.127.649.6+22.1
- GSM8KLFM2.5-1.2B-Thinking by 1669.685.6+16
- IFEvalLFM2.5-1.2B-Thinking by 8.380.188.4+8.3
- AA-OmniscienceGranite 4.0 H 1B by 7.6-72.3-80+7.6
- BFCL v3LFM2.5-1.2B-Thinking by 6.350.757+6.3
- AA Agentic Indextie6.56.5tie
- AA Intelligencetie5.25.2tie
- τ²-Bench Telecom (AA run)tie19.619.6tie
Questions people ask
Which is better, Granite 4.0 H 1B or LFM2.5-1.2B-Thinking?
Granite 4.0 H 1B and LFM2.5-1.2B-Thinking 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-Thinking 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-Thinking 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.