Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d272Policy30d66, 14 pendingSources1,015

Llama 3.1 70B Instruct vs Llama 3.2 Instruct 11B (Vision)

Meta · released

Wins 3 of 5 areas

Coding · Facts · Following instructions

Meta · released

Wins 1 of 5 areas

Long documents

Llama 3.1 70B Instruct is the stronger all-rounder.Llama 3.2 Instruct 11B (Vision) is cheaper and better at long documents.

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.

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 3.1 70B Instruct$0.56 to read · $0.56 to write$1.12Price from Artificial Analysis
Llama 3.2 Instruct 11B (Vision)$0.34 to read · $0.34 to write$0.69Price from Artificial Analysis

Llama 3.2 Instruct 11B (Vision) costs 38% 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 3.1 70B Instruct pulls ahead

  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.8points aheadLlama 3.1 70B Instruct40.9Llama 3.2 Instruct 11B (Vision)22.1
  • Code for real scientific research problemsSciCode+15.5points aheadLlama 3.1 70B Instruct26.7Llama 3.2 Instruct 11B (Vision)11.2
  • Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+9.1points aheadLlama 3.1 70B Instruct19.7Llama 3.2 Instruct 11B (Vision)10.6

Where Llama 3.2 Instruct 11B (Vision) pulls ahead

  • Reasons across sets of long documentsAA-LCR+4.7points aheadLlama 3.2 Instruct 11B (Vision)12.7Llama 3.1 70B Instruct8
  • Very hard expert questions across many subjectsHumanity's Last Exam+1points aheadLlama 3.2 Instruct 11B (Vision)5.5Llama 3.1 70B Instruct4.5

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.

CodingLlama 3.1 70B Instruct

Full coding ranking

ReasoningEven

Full reasoning ranking

FactsLlama 3.1 70B Instruct

Full facts ranking

Long documentsLlama 3.2 Instruct 11B (Vision)
  • AA-LCRLlama 3.2 Instruct 11B (Vision) by 4.7812.7+4.7

Full long documents ranking

Following instructionsLlama 3.1 70B Instruct
  • IFBenchLlama 3.1 70B Instruct by 434.430.4+4

Full following instructions ranking

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.

Questions people ask

Which is better, Llama 3.1 70B Instruct or Llama 3.2 Instruct 11B (Vision)?

Llama 3.1 70B Instruct wins three of the five areas where both have results: coding, facts and following instructions. Llama 3.2 Instruct 11B (Vision) wins long documents, and costs 38% less. They are level on reasoning.

Which is better for coding?

Llama 3.1 70B Instruct. It wins 2 of the 2 coding tests both models report; Llama 3.2 Instruct 11B (Vision) wins none.

Which is cheaper?

Llama 3.1 70B Instruct costs $0.56 per million input tokens and $0.56 per million output tokens; Llama 3.2 Instruct 11B (Vision) costs $0.34 and $0.34. That makes Llama 3.2 Instruct 11B (Vision) about 38% 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.