DeepSeek-R1-Distill-Qwen-7B is the stronger all-rounder.Granite 3.3 8B Instruct is cheaper.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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 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.
Granite 3.3 8B Instruct costs 7% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-R1-Distill-Qwen-7B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+15.3points ahead
Where Granite 3.3 8B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningDeepSeek-R1-Distill-Qwen-7B
- GPQA DiamondDeepSeek-R1-Distill-Qwen-7B by 15.349.133.8+15.3
Other results14 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.
- AIME 2024DeepSeek-R1-Distill-Qwen-7B by 47.455.58.1+47.4
- AlpacaEval-2.0Granite 3.3 8B Instruct by 47.315.362.7+47.3
- Arena HardGranite 3.3 8B Instruct by 47.210.457.6+47.2
- AttaQGranite 3.3 8B Instruct by 4642.588.5+46
- MATH-500 (EM)DeepSeek-R1-Distill-Qwen-7B by 23.892.869+23.8
- TruthfulQAGranite 3.3 8B Instruct by 19.847.166.9+19.8
- PopQAGranite 3.3 8B Instruct by 16.39.926.2+16.3
- MMLUGranite 3.3 8B Instruct by 14.850.765.5+14.8
- IFEvalGranite 3.3 8B Instruct by 14.360.574.8+14.3
- HumanEvalGranite 3.3 8B Instruct by 9.879.989.7+9.8
- HumanEval+Granite 3.3 8B Instruct by 7.778.486.1+7.7
- DROPGranite 3.3 8B Instruct by 7.651.859.4+7.6
- GSM8KGranite 3.3 8B Instruct by 2.478.580.9+2.4
- BigBenchHardGranite 3.3 8B Instruct by 1.767.469.1+1.7
Questions people ask
Which is better, DeepSeek-R1-Distill-Qwen-7B or Granite 3.3 8B Instruct?
DeepSeek-R1-Distill-Qwen-7B wins the one area where both have results: reasoning. Granite 3.3 8B Instruct wins none, but costs 7% less.
Which is cheaper?
DeepSeek-R1-Distill-Qwen-7B costs $0.15 per million input tokens and $0.15 per million output tokens; Granite 3.3 8B Instruct costs $0.03 and $0.25. That makes Granite 3.3 8B Instruct about 7% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.