Granite 4.0 H Tiny vs LFM2-8B-A1B (Non-Reasoning)
Wins 1 of 3 areas
Coding
Wins 2 of 3 areas
Reasoning · Following instructions
LFM2-8B-A1B (Non-Reasoning) is the stronger all-rounder.Granite 4.0 H Tiny is better at coding.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Coding, 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 LFM2-8B-A1B (Non-Reasoning) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.9points ahead
Where Granite 4.0 H Tiny pulls ahead
- Recent programming contest problemsLiveCodeBench v6+5.7points 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.
ReasoningLFM2-8B-A1B (Non-Reasoning)
- GPQA DiamondLFM2-8B-A1B (Non-Reasoning) by 7.926.534.4+7.9
Following instructionsLFM2-8B-A1B (Non-Reasoning)
- IFBenchLFM2-8B-A1B (Non-Reasoning) by 7.918.426.3+7.9
Other results15 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)LFM2-8B-A1B (Non-Reasoning) by 1658.274.2+16
- MATH500 (Pass@1)LFM2-8B-A1B (Non-Reasoning) by 15.659.274.8+15.6
- AIME25 no toolsLFM2-8B-A1B (Non-Reasoning) by 15.14.920+15.1
- BFCL v3Granite 4.0 H Tiny by 11.856.945.1+11.8
- τ²-Bench (Retail)Granite 4.0 H Tiny by 11.418.47+11.4
- LCB v5Granite 4.0 H Tiny by 5.927.321.4+5.9
- GSMPlusLFM2-8B-A1B (Non-Reasoning) by 5.759.164.8+5.7
- MMLU-ProLFM2-8B-A1B (Non-Reasoning) by 5.43237.4+5.4
- HumanEval+Granite 4.0 H Tiny by 4.373.869.5+4.3
- IFEvalGranite 4.0 H Tiny by 3.581.177.6+3.5
- Tau² TelecomGranite 4.0 H Tiny by 3.116.713.6+3.1
- BFCLv4Granite 4.0 H Tiny by 328.525.5+3
- MMLUGranite 4.0 H Tiny by 266.864.8+2
- MGSMGranite 4.0 H Tiny by 1.373.772.4+1.3
- MMMLUtie56.155.3tie
Questions people ask
Which is better, Granite 4.0 H Tiny or LFM2-8B-A1B (Non-Reasoning)?
LFM2-8B-A1B (Non-Reasoning) wins two of the three areas where both have results: reasoning and following instructions. Granite 4.0 H Tiny wins coding.
Which is better for coding?
Granite 4.0 H Tiny. It wins the one coding test both models report.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.