The two are evenly matched.
Scores updated · 10 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.
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 Claude 3 Haiku pulls ahead
No clear win on a test scored out of 100.
Where Phi 3 Vision 128K Instruct pulls ahead
- Math problems shown in pictures and chartsMathVista+11.3points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsEven
- LMArena · VisionClaude 3 Haiku by 138.4 rating points950.1811.7+138.4 rating
- MathVistaPhi 3 Vision 128K Instruct by 11.333.244.5+11.3
- MMMUtie40.740.4tie
Other results7 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.
- ChartQAPhi 3 Vision 128K Instruct by 22.159.381.4+22.1
- ScienceQAPhi 3 Vision 128K Instruct by 18.87290.8+18.8
- MMBenchPhi 3 Vision 128K Instruct by 18.162.480.5+18.1
- AI2DPhi 3 Vision 128K Instruct by 16.460.376.7+16.4
- POPEPhi 3 Vision 128K Instruct by 11.474.485.8+11.4
- TextVQAPhi 3 Vision 128K Instruct by 8.262.770.9+8.2
- InterGPSPhi 3 Vision 128K Instruct by 632.138.1+6
Questions people ask
Which is better, Claude 3 Haiku or Phi 3 Vision 128K Instruct?
Neither wins more tests than the other in any of the one area where both have results.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.