Llama 3.2 Instruct 11B (Vision) vs Llama 3 Instruct 8B
Wins 3 of 5 areas
Facts · Long documents · Following instructions
Wins 1 of 5 areas
Reasoning
Llama 3.2 Instruct 11B (Vision) is the stronger all-rounder.Llama 3 Instruct 8B is cheaper and better at reasoning.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- FactsGetting facts right instead of making them up10Llama 3.2 Instruct 11B (Vision)1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Llama 3.2 Instruct 11B (Vision)1 of 1 test
- Following instructionsDoing exactly what it is asked10Llama 3.2 Instruct 11B (Vision)1 of 1 test
- ReasoningHard problems that need careful thinking01Llama 3 Instruct 8B1 of 3 tests · 2 ties
- CodingWriting and fixing software00Even0 each · 2 ties
Long documents and following instructions rest on a single test each.
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.
Llama 3 Instruct 8B costs 72% less for the same work.
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 11B (Vision) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.8points ahead
Where Llama 3 Instruct 8B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.5points ahead
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.
ReasoningLlama 3 Instruct 8B
- GPQA DiamondLlama 3 Instruct 8B by 7.522.129.6+7.5
- Humanity's Last Examtie5.55.1tie
- CritPttie00tie
FactsLlama 3.2 Instruct 11B (Vision)
- AA-Omniscience · Non-hallucinationLlama 3.2 Instruct 11B (Vision) by 7.918.110.2+7.9
- AA-Omniscience · Accuracytie10.610.4tie
Long documentsLlama 3.2 Instruct 11B (Vision)
- AA-LCRLlama 3.2 Instruct 11B (Vision) by 12.712.70+12.7
Following instructionsLlama 3.2 Instruct 11B (Vision)
- IFBenchLlama 3.2 Instruct 11B (Vision) by 5.830.424.6+5.8
Other results11 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.
- MATHLlama 3.2 Instruct 11B (Vision) by 34.873.939.1+34.8
- GSM8KLlama 3.2 Instruct 11B (Vision) by 32.482.349.9+32.4
- τ²-Bench Telecom (AA run)Llama 3.2 Instruct 11B (Vision) by 14.614.60+14.6
- naturalquestions_closedbookLlama 3 Instruct 8B by 14.423.437.8+14.4
- MMLULlama 3 Instruct 8B by 9.151.160.1+9.1
- AA-OmniscienceLlama 3.2 Instruct 11B (Vision) by 7.5-62.6-70.1+7.5
- AA Agentic IndexLlama 3.2 Instruct 11B (Vision) by 4.94.90+4.9
- OpenBookQALlama 3 Instruct 8B by 4.272.476.6+4.2
- AA Intelligencetie5.44.8tie
- Artificial Analysis Coding Indextie4.24tie
- NarrativeQAtie75.675.4tie
Questions people ask
Which is better, Llama 3.2 Instruct 11B (Vision) or Llama 3 Instruct 8B?
Llama 3.2 Instruct 11B (Vision) wins three of the five areas where both have results: facts, long documents and following instructions. Llama 3 Instruct 8B wins reasoning, and costs 72% less. They are level on coding.
Which is better for coding?
Neither. All 2 coding tests both models report are ties.
Which is cheaper?
Llama 3.2 Instruct 11B (Vision) costs $0.34 per million input tokens and $0.34 per million output tokens; Llama 3 Instruct 8B costs $0.04 and $0.14. That makes Llama 3 Instruct 8B about 72% cheaper for the same work.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.