Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Granite 4.0 H Tiny vs LFM2-700M

IBM · released

Wins 0 of 2 areas

—

Liquid AI · released

Wins 2 of 2 areas

Reasoning · Following instructions

LFM2-700M is the stronger all-rounder.

Scores updated · 7 tests both models report · How we compare

Where each one wins

Tests won in each of the two 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.

Reasoning 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 LFM2-700M pulls ahead

  • Follows unfamiliar, precisely checkable instructionsIFBench+2.2points aheadLFM2-700M20.6Granite 4.0 H Tiny18.4
  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+2points aheadLFM2-700M28.5Granite 4.0 H Tiny26.5

Where Granite 4.0 H Tiny pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 7 tests both models report. The winning score is in its model's colour; marks a score checked independently.

ReasoningLFM2-700M

Full reasoning ranking

Following instructionsLFM2-700M
  • IFBenchLFM2-700M by 2.218.420.6+2.2

Full following instructions ranking

Other results5 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 Tiny by 36.282.646.4+36.2
  • MGSMGranite 4.0 H Tiny by 28.373.745.4+28.3
  • MMLUGranite 4.0 H Tiny by 16.966.849.9+16.9
  • MMMLUGranite 4.0 H Tiny by 12.856.143.3+12.8
  • IFEvalGranite 4.0 H Tiny by 8.981.172.2+8.9

Questions people ask

Which is better, Granite 4.0 H Tiny or LFM2-700M?

LFM2-700M wins all two areas where both have results: reasoning and following instructions. Granite 4.0 H Tiny wins none.

How do you compare the two?

We use the 7 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.