Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,014

Llama 3.1 8B Instruct vs Llama 3.3 70B Instruct

Meta · released

Wins 1 of 6 areas

Long documents

Meta · released

Wins 2 of 6 areas

Coding · Following instructions

Llama 3.3 70B Instruct wins more areas, narrowly.Llama 3.1 8B Instruct is cheaper and better at long documents.

Scores updated · 31 tests both models report · How we compare

Where each one wins

Tests won in each of the six 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 8B Instruct$0.02 to read · $0.05 to write$0.07Price from Artificial Analysis
Llama 3.3 70B Instruct$0.71 to read · $0.72 to write$1.43Price from Artificial Analysis

Llama 3.1 8B Instruct costs 95% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where Llama 3.3 70B Instruct pulls ahead

  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+23.9points aheadLlama 3.3 70B Instruct49.8Llama 3.1 8B Instruct25.9
  • Follows unfamiliar, precisely checkable instructionsIFBench+18.5points aheadLlama 3.3 70B Instruct47.1Llama 3.1 8B Instruct28.6
  • Code for real scientific research problemsSciCode+12.8points aheadLlama 3.3 70B Instruct26Llama 3.1 8B Instruct13.2

Where Llama 3.1 8B Instruct pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.2points aheadLlama 3.1 8B Instruct57Llama 3.3 70B Instruct9.8
  • Reasons across sets of long documentsAA-LCR+2.3points aheadLlama 3.1 8B Instruct18Llama 3.3 70B Instruct15.7
  • Very hard expert questions across many subjectsHumanity's Last Exam+1.7points aheadLlama 3.1 8B Instruct5.3Llama 3.3 70B Instruct3.6

Every test, side by side

All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingLlama 3.3 70B Instruct

Full coding ranking

AgentsEven

Full agents ranking

ReasoningEven

Full reasoning ranking

FactsEven

Full facts ranking

Long documentsLlama 3.1 8B Instruct
  • AA-LCRLlama 3.1 8B Instruct by 2.31815.7+2.3

Full long documents ranking

Following instructionsLlama 3.3 70B Instruct
  • IFBenchLlama 3.3 70B Instruct by 18.528.647.1+18.5

Full following instructions ranking

Other results20 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 8B Instruct or Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct wins two of the six areas where both have results: coding and following instructions. Llama 3.1 8B Instruct wins long documents, and costs 95% less. They are level on agents, reasoning and facts.

Which is better for coding?

Llama 3.3 70B Instruct. It wins 2 of the 2 coding tests both models report; Llama 3.1 8B Instruct wins none.

Which is cheaper?

Llama 3.1 8B Instruct costs $0.02 per million input tokens and $0.05 per million output tokens; Llama 3.3 70B Instruct costs $0.71 and $0.72. That makes Llama 3.1 8B Instruct about 95% cheaper for the same work.

How do you compare the two?

We use the 31 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 20 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.