Llama 3.2 Instruct 90B (Vision) vs Nova Lite
Wins 2 of 3 areas
Coding · Images and charts
Wins 0 of 3 areas
—
Llama 3.2 Instruct 90B (Vision) is the stronger all-rounder.
Scores updated · 14 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas 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.
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 Llama 3.2 Instruct 90B (Vision) pulls ahead
Where Nova Lite pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3.2 Instruct 90B (Vision)
- SciCodeLlama 3.2 Instruct 90B (Vision) by 10.12413.9+10.1
Images and chartsLlama 3.2 Instruct 90B (Vision)
Other results9 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.
- naturalquestions_closedbookLlama 3.2 Instruct 90B (Vision) by 10.545.735.2+10.5
- DocVQANova Lite by 2.390.192.4+2.3
- OpenBookQALlama 3.2 Instruct 90B (Vision) by 1.494.292.8+1.4
- ChartQANova Lite by 1.385.586.8+1.3
- MATHLlama 3.2 Instruct 90B (Vision) by 1.279.177.9+1.2
- MMLULlama 3.2 Instruct 90B (Vision) by 170.369.3+1
- GSM8Ktie93.694.5tie
- NarrativeQAtie77.776.8tie
- AA Intelligencetie6.46.7tie
Questions people ask
Which is better, Llama 3.2 Instruct 90B (Vision) or Nova Lite?
Llama 3.2 Instruct 90B (Vision) wins two of the three areas where both have results: coding and images and charts. Nova Lite wins none. They are level on reasoning.
Which is better for coding?
Llama 3.2 Instruct 90B (Vision). It wins the one coding test both models report.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.