Scores updated · 15 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$0.47 to read · $0.49 to writePrice from Artificial Analysis
Step3.5 Flash BaseNo current price is tracked.
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.
Other results15 tests
- SimpleQAStep3.5 Flash Base by 22.59.131.6+22.5
- MATHQwen2.5 Instruct 72B by 21.688.466.8+21.6
- Chinese SimpleQA (C-SimpleQA)Step3.5 Flash Base by 14.848.463.2+14.8
- MBPPQwen2.5 Instruct 72B by 8.888.279.4+8.8
- MMLUStep3.5 Flash Base by 8.87785.8+8.8
- MMLU-ProQwen2.5 Instruct 72B by 8.871.162.3+8.8
- BBHStep3.5 Flash Base by 8.479.888.2+8.4
- GSM8KQwen2.5 Instruct 72B by 7.695.888.2+7.6
- MBPP+ (EvalPlus-augmented)Qwen2.5 Instruct 72B by 6.47770.6+6.4
- HumanEvalQwen2.5 Instruct 72B by 5.586.681.1+5.5
- HellaSwagStep3.5 Flash Base by 5.484.890.2+5.4
- WinoGrandeQwen2.5 Instruct 72B by 3.282.379.1+3.2
- MMLU-ReduxStep3.5 Flash Base by 2.486.889.2+2.4
- CMMLUtie89.588.9tie
- C-Evaltie89.289.6tie
Questions people ask
How do you compare the two?
We use the 15 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.