Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Granite 4.1 8B vs Llama 3.1 8B Instruct

IBM · released

Wins 3 of 6 areas

Coding · Agents · Following instructions

Meta · released

Wins 1 of 6 areas

Long documents

Granite 4.1 8B wins more areas, narrowly.Llama 3.1 8B Instruct is cheaper and better at long documents.

Scores updated · 25 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.

Granite 4.1 8B$0.05 to read · $0.10 to write$0.15Price from ibm-granite
Llama 3.1 8B Instruct$0.02 to read · $0.05 to write$0.07Price from Artificial Analysis

Llama 3.1 8B Instruct costs 53% less for the same work.

The biggest differences

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

Where Granite 4.1 8B pulls ahead

  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+17.4points aheadGranite 4.1 8B43.3Llama 3.1 8B Instruct25.9
  • Follows unfamiliar, precisely checkable instructionsIFBench+10points aheadGranite 4.1 8B38.6Llama 3.1 8B Instruct28.6
  • Code for real scientific research problemsSciCode+8.6points aheadGranite 4.1 8B21.8Llama 3.1 8B Instruct13.2

Where Llama 3.1 8B Instruct pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+44.1points aheadLlama 3.1 8B Instruct57Granite 4.1 8B12.9
  • Reasons across sets of long documentsAA-LCR+4.7points aheadLlama 3.1 8B Instruct18Granite 4.1 8B13.3
  • Very hard expert questions across many subjectsHumanity's Last Exam+1.5points aheadLlama 3.1 8B Instruct5.3Granite 4.1 8B3.8

Every test, side by side

All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingGranite 4.1 8B

Full coding ranking

AgentsGranite 4.1 8B

Full agents ranking

ReasoningEven

Full reasoning ranking

FactsEven

Full facts ranking

Long documentsLlama 3.1 8B Instruct
  • AA-LCRLlama 3.1 8B Instruct by 4.713.318+4.7

Full long documents ranking

Following instructionsGranite 4.1 8B
  • IFBenchGranite 4.1 8B by 1038.628.6+10

Full following instructions ranking

Other results14 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, Granite 4.1 8B or Llama 3.1 8B Instruct?

Granite 4.1 8B wins three of the six areas where both have results: coding, agents and following instructions. Llama 3.1 8B Instruct wins long documents, and costs 53% less. They are level on reasoning and facts.

Which is better for coding?

Granite 4.1 8B. It wins 1 of the 2 coding tests both models report; Llama 3.1 8B Instruct wins none, and 1 is a tie.

Which is cheaper?

Granite 4.1 8B costs $0.05 per million input tokens and $0.10 per million output tokens; Llama 3.1 8B Instruct costs $0.02 and $0.05. That makes Llama 3.1 8B Instruct about 53% cheaper for the same work.

How do you compare the two?

We use the 25 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 14 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.