Hy4 flash is the stronger all-rounder.
Scores updated · 25 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.
Images and charts rests on a single test.
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 Hy4 flash pulls ahead
- Harder college exam questions with imagesMMMU-Pro+23.8points ahead
Where Hy4-flash-base pulls ahead
No clear win on a test scored out of 100.
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 results24 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.
- AGIEval (Chinese)tie90.690.6tie
- AGIEval-Entie75.475.4tie
- ARC-Challengetie9595tie
- Belebele (5-language subset)tie93.893.8tie
- C-Evaltie9292tie
- C3tie77.377.3tie
- Chinese SimpleQA (C-SimpleQA)tie74.674.6tie
- CMMLUtie91.691.6tie
- CV-Benchtie83.483.4tie
- HellaSwagtie85.285.2tie
- Includetie82.882.8tie
- KOR-Benchtie54.754.7tie
- MBPP+ (EvalPlus-augmented)tie73.773.7tie
- MMLU-Protie71.171.1tie
- MMLU-Reduxtie87.687.6tie
- OCW Coursestie6464tie
- PIQAtie84.484.4tie
- RealWorldQAtie71.171.1tie
- SimpleQAtie37.537.5tie
- SimpleVQAtie48.548.5tie
- Social IQAtie80.180.1tie
- SuperGPQAtie57.857.8tie
- TextVQAtie73.473.4tie
- U-MATHtie69.869.8tie
Questions people ask
Which is better, Hy4 flash or Hy4-flash-base?
Hy4 flash wins the one area where both have results: images and charts. Hy4-flash-base wins none.
How do you compare the two?
We use the 25 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 24 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.