GPT-4o vs QwQ 32B Preview
Wins 1 of 4 areas
Long documents
Wins 3 of 4 areas
Coding · Reasoning · Following instructions
QwQ 32B Preview is the stronger all-rounder.GPT-4o is better at long documents.
Scores updated · 18 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Long documents and following instructions rest on a single test each.
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.
QwQ 32B Preview costs 92% 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 QwQ 32B Preview pulls ahead
- Recent programming contest problemsLiveCodeBench v6+8.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5.6points ahead
Where GPT-4o pulls ahead
- Reasons across sets of long documentsAA-LCR+29.3points 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.
CodingQwQ 32B Preview
- LiveCodeBench v6QwQ 32B Preview by 8.230.939.1+8.2
- SciCodeQwQ 32B Preview by 2.533.335.8+2.5
ReasoningQwQ 32B Preview
- GPQA DiamondQwQ 32B Preview by 6.752.659.3+6.7
- Humanity's Last ExamQwQ 32B Preview by 5.61.87.3+5.6
Following instructionsQwQ 32B Preview
- IFBenchQwQ 32B Preview by 2.83638.8+2.8
Other results12 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.
- Codeforces (Rating)QwQ 32B Preview by 557 rating points7591316+557 rating
- AIME 2024QwQ 32B Preview by 40.79.350+40.7
- MMLU-ProGPT-4o by 22.774.752+22.7
- AIME 2025QwQ 32B Preview by 21.611.733.3+21.6
- MATH-500 (EM)QwQ 32B Preview by 1674.690.6+16
- MATH500 (Pass@1)QwQ 32B Preview by 1674.690.6+16
- DROP (3-shot F1)GPT-4o by 12.583.771.2+12.5
- LiveCodeBenchQwQ 32B Preview by 11.738.350+11.7
- Aider-PolyglotGPT-4o by 9.830.720.9+9.8
- IFEvalQwQ 32B Preview by 2.98183.9+2.9
- AA IntelligenceQwQ 32B Preview by 2.27.39.5+2.2
- SuperGPQAQwQ 32B Preview by 1.242.443.6+1.2
Questions people ask
Which is better, GPT-4o or QwQ 32B Preview?
QwQ 32B Preview wins three of the four areas where both have results: coding, reasoning and following instructions. GPT-4o wins long documents.
Which is better for coding?
QwQ 32B Preview. It wins 2 of the 2 coding tests both models report; GPT-4o wins none.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; QwQ 32B Preview costs $0.66 and $1.00. That makes QwQ 32B Preview about 92% cheaper for the same work.
How do you compare the two?
We use the 18 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.