Hy3-preview-Base is the stronger all-rounder.
Scores updated · 20 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.
Coding 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 Hy3-preview-Base pulls ahead
- Recent programming contest problemsLiveCodeBench v6+8.6points ahead
Where Kimi K2 Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results19 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.
- SimpleQAKimi K2 Base by 8.826.535.3+8.8
- SuperGPQAHy3-preview-Base by 6.951.644.7+6.9
- MATHHy3-preview-Base by 6.176.370.2+6.1
- Chinese SimpleQA (C-SimpleQA)Kimi K2 Base by 4.969.774.6+4.9
- MBPP+ (EvalPlus-augmented)Hy3-preview-Base by 4.978.773.8+4.9
- MMLU-ProKimi K2 Base by 3.465.869.2+3.4
- GSM8KHy3-preview-Base by 3.395.492.1+3.3
- MMLU-ReduxKimi K2 Base by 3.386.990.2+3.3
- CRUXEval-I (input prediction)Hy3-preview-Base by 3.271.268+3.2
- IncludeHy3-preview-Base by 2.978.675.7+2.9
- C-EvalKimi K2 Base by 2.789.892.5+2.7
- MMMLUHy3-preview-Base by 2.680.277.6+2.6
- DROPHy3-preview-Base by 1.985.583.6+1.9
- CMMLUKimi K2 Base by 1.389.690.9+1.3
- CRUXEval-O (output prediction)Kimi K2 Base by 1.268.469.6+1.2
- PIQAtie84.484.9tie
- CMathtie91.290.8tie
- MMLUtie87.487.8tie
- ARC-Challengetie9696.2tie
Questions people ask
Which is better, Hy3-preview-Base or Kimi K2 Base?
Hy3-preview-Base wins the one area where both have results: coding. Kimi K2 Base wins none.
Which is better for coding?
Hy3-preview-Base. It wins the one coding test both models report.
How do you compare the two?
We use the 20 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 19 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.