Scores updated · 13 tests both models report · How we compare
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.
Qwen2.5 Instruct 72B costs 25% less for the same work.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results13 tests
- HumanEvalQwen2.5 Instruct 72B by 34.851.886.6+34.8
- MBPPQwen2.5 Instruct 72B by 25.662.688.2+25.6
- ARC-ChallengeQwen2.5 Instruct 72B by 23.171.494.5+23.1
- GSM8KQwen2.5 Instruct 72B by 21.87495.8+21.8
- MATHQwen2.5 Instruct 72B by 13.874.688.4+13.8
- MMLUQwen2.5 Instruct 72B by 10.666.477+10.6
- NarrativeQAGemma 2 27B IT by 4.57974.5+4.5
- OpenBookQAQwen2.5 Instruct 72B by 4.491.896.2+4.4
- HellaSwagGemma 2 27B IT by 1.686.484.8+1.6
- WinoGrandeGemma 2 27B IT by 1.483.782.3+1.4
- NaturalQuestionsGemma 2 27B IT by 1.334.533.2+1.3
- naturalquestions_closedbooktie35.335.9tie
- PIQAtie83.282.6tie
Questions people ask
Which is cheaper?
Gemma 2 27B IT costs $0.65 per million input tokens and $0.65 per million output tokens; Qwen2.5 Instruct 72B costs $0.47 and $0.49. That makes Qwen2.5 Instruct 72B about 25% cheaper for the same work.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.