Qwen2.5 Coder Instruct 7B is the stronger all-rounder.
Scores updated · 8 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.
Coding rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen2.5 Coder Instruct 7B pulls ahead
- Code for real scientific research problemsSciCode+2.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.5points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.5points ahead
Where Granite 4.1 3B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 8 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen2.5 Coder Instruct 7B
- SciCodeQwen2.5 Coder Instruct 7B by 2.911.914.8+2.9
ReasoningQwen2.5 Coder Instruct 7B
- GPQA DiamondQwen2.5 Coder Instruct 7B by 2.531.433.9+2.5
- Humanity's Last ExamQwen2.5 Coder Instruct 7B by 1.53.44.9+1.5
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.
- CRUXEval-O (output prediction)Qwen2.5 Coder Instruct 7B by 15.240.856+15.2
- MBPPQwen2.5 Coder Instruct 7B by 12.371.283.5+12.3
- HumanEvalQwen2.5 Coder Instruct 7B by 6.781.788.4+6.7
- MultiPL-EQwen2.5 Coder Instruct 7B by 6.352.558.8+6.3
- AA Intelligencetie5.95.8tie
Questions people ask
Which is better, Granite 4.1 3B or Qwen2.5 Coder Instruct 7B?
Qwen2.5 Coder Instruct 7B wins all two areas where both have results: coding and reasoning. Granite 4.1 3B wins none.
Which is better for coding?
Qwen2.5 Coder Instruct 7B. It wins the one coding test both models report.
How do you compare the two?
We use the 8 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 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.