Hy3-preview-Base is the stronger all-rounder.
Scores updated · 18 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+10points ahead
Where DeepSeek-V3.2-Exp-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results17 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.
- MATHHy3-preview-Base by 16.260.176.3+16.2
- GSM8KHy3-preview-Base by 1184.495.4+11
- MBPP+ (EvalPlus-augmented)Hy3-preview-Base by 8.969.878.7+8.9
- SuperGPQAHy3-preview-Base by 843.651.6+8
- CRUXEval-I (input prediction)Hy3-preview-Base by 7.363.971.2+7.3
- CRUXEval-O (output prediction)DeepSeek-V3.2-Exp-Base by 6.574.968.4+6.5
- MMLU-ReduxDeepSeek-V3.2-Exp-Base by 3.590.486.9+3.5
- MMLU-ProHy3-preview-Base by 2.563.365.8+2.5
- Chinese SimpleQA (C-SimpleQA)Hy3-preview-Base by 1.76869.7+1.7
- IncludeHy3-preview-Base by 1.477.278.6+1.4
- C-EvalDeepSeek-V3.2-Exp-Base by 1.29189.8+1.2
- DROPDeepSeek-V3.2-Exp-Base by 1.186.685.5+1.1
- ARC-Challengetie95.296tie
- CMMLUtie88.989.6tie
- PIQAtie85.184.4tie
- SimpleQAtie2726.5tie
- MMLUtie87.887.4tie
Questions people ask
Which is better, DeepSeek-V3.2-Exp-Base or Hy3-preview-Base?
Hy3-preview-Base wins the one area where both have results: coding. DeepSeek-V3.2-Exp-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 18 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 17 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.