The two are evenly matched.Kimi K2 Base is better at coding; Qwen2.5 Instruct 72B at reasoning.
Scores updated · 25 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 and reasoning 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Kimi K2 Base pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+4.4points ahead
Where Qwen2.5 Instruct 72B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1points ahead
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results23 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.
- OpenBookQAQwen2.5 Instruct 72B by 45.450.896.2+45.4
- Chinese SimpleQA (C-SimpleQA)Kimi K2 Base by 26.274.648.4+26.2
- SimpleQAKimi K2 Base by 26.235.39.1+26.2
- MATHQwen2.5 Instruct 72B by 18.270.288.4+18.2
- MMLUKimi K2 Base by 10.887.877+10.8
- HellaSwagKimi K2 Base by 9.894.684.8+9.8
- CRUXEval-O (output prediction)Kimi K2 Base by 9.769.659.9+9.7
- MGSMKimi K2 Base by 985.276.2+9
- BBHKimi K2 Base by 8.988.779.8+8.9
- CRUXEval-I (input prediction)Kimi K2 Base by 8.96859.1+8.9
- HumanEvalQwen2.5 Instruct 72B by 8.478.286.6+8.4
- DROPKimi K2 Base by 6.983.676.7+6.9
- GSM8KQwen2.5 Instruct 72B by 3.792.195.8+3.7
- MMLU-ReduxKimi K2 Base by 3.490.286.8+3.4
- C-EvalKimi K2 Base by 3.392.589.2+3.3
- MBPP+ (EvalPlus-augmented)Qwen2.5 Instruct 72B by 3.273.877+3.2
- WinoGrandeKimi K2 Base by 385.382.3+3
- MMMLUKimi K2 Base by 2.877.674.8+2.8
- PIQAKimi K2 Base by 2.384.982.6+2.3
- MMLU-ProQwen2.5 Instruct 72B by 1.969.271.1+1.9
- ARC-ChallengeKimi K2 Base by 1.796.294.5+1.7
- CMMLUKimi K2 Base by 1.490.989.5+1.4
- MBPPtie8988.2tie
Questions people ask
Which is better, Kimi K2 Base or Qwen2.5 Instruct 72B?
Kimi K2 Base and Qwen2.5 Instruct 72B each win one of the two areas where both have results. Kimi K2 Base wins coding; Qwen2.5 Instruct 72B wins reasoning.
Which is better for coding?
Kimi K2 Base. It wins the one coding test both models report.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 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.