Granite 4.0 H 1B vs Qwen3 1.7B (instruct)
Wins 1 of 2 areas
Following instructions
Wins 1 of 2 areas
Reasoning
The two are evenly matched.Granite 4.0 H 1B is better at following instructions; Qwen3 1.7B (instruct) at reasoning.
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 Granite 4.0 H 1B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+4.9points ahead
Where Qwen3 1.7B (instruct) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.6points ahead
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.
ReasoningQwen3 1.7B (instruct)
- GPQA DiamondQwen3 1.7B (instruct) by 8.626.334.9+8.6
Following instructionsGranite 4.0 H 1B
- IFBenchGranite 4.0 H 1B by 4.926.221.3+4.9
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 1B by 35.969.633.7+35.9
- MATH-500 (EM)Qwen3 1.7B (instruct) by 23.247.270.4+23.2
- MMLU-ProQwen3 1.7B (instruct) by 15.327.642.9+15.3
- IFEvalGranite 4.0 H 1B by 6.480.173.7+6.4
- BFCL v3Granite 4.0 H 1B by 4.450.746.3+4.4
Questions people ask
Which is better, Granite 4.0 H 1B or Qwen3 1.7B (instruct)?
Granite 4.0 H 1B and Qwen3 1.7B (instruct) each win one of the two areas where both have results. Granite 4.0 H 1B wins following instructions; Qwen3 1.7B (instruct) wins reasoning.
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.