Kimi K2 Base is the stronger all-rounder.
Scores updated · 16 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.
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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.4points ahead
Where Mistral 7B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 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.
- MATHKimi K2 Base by 57.170.213.1+57.1
- HumanEvalKimi K2 Base by 48.978.229.3+48.9
- C-EvalKimi K2 Base by 45.192.547.4+45.1
- EvalPlusKimi K2 Base by 43.980.336.4+43.9
- GSM8KKimi K2 Base by 39.992.152.2+39.9
- MMLU-ProKimi K2 Base by 38.369.230.9+38.3
- MBPPKimi K2 Base by 37.98951.1+37.9
- ARC-ChallengeKimi K2 Base by 36.296.260+36.2
- BBHKimi K2 Base by 32.688.756.1+32.6
- OpenBookQAMistral 7B by 2950.879.8+29
- MMLUKimi K2 Base by 23.687.864.2+23.6
- HellaSwagKimi K2 Base by 11.494.683.2+11.4
- TriviaQAKimi K2 Base by 9.985.175.2+9.9
- PIQAKimi K2 Base by 7.284.977.7+7.2
- WinoGrandeKimi K2 Base by 6.985.378.4+6.9
Questions people ask
Which is better, Kimi K2 Base or Mistral 7B?
Kimi K2 Base wins the one area where both have results: reasoning. Mistral 7B wins none.
How do you compare the two?
We use the 16 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 15 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.