Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Gemma 2 27B IT vs Llama 3.1 Instruct 405B

Google · released

Meta · released

Scores updated · 13 tests both models report · How we compare

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.

Gemma 2 27B IT$0.65 to read · $0.65 to write$1.30Price from google
Llama 3.1 Instruct 405BNo current price is tracked.

Every test, side by side

All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Other results13 tests
  • HumanEvalLlama 3.1 Instruct 405B by 37.251.889+37.2
  • ARC-ChallengeLlama 3.1 Instruct 405B by 25.571.496.9+25.5
  • GSM8KLlama 3.1 Instruct 405B by 22.87496.8+22.8
  • MMLULlama 3.1 Instruct 405B by 22.266.488.6+22.2
  • naturalquestions_closedbookLlama 3.1 Instruct 405B by 10.335.345.6+10.3
  • NaturalQuestionsLlama 3.1 Instruct 405B by 734.541.5+7
  • MBPPLlama 3.1 Instruct 405B by 5.862.668.4+5.8
  • NarrativeQAGemma 2 27B IT by 4.17974.9+4.1
  • HellaSwagLlama 3.1 Instruct 405B by 2.886.489.2+2.8
  • PIQALlama 3.1 Instruct 405B by 2.783.285.9+2.7
  • OpenBookQALlama 3.1 Instruct 405B by 2.291.894+2.2
  • WinoGrandeLlama 3.1 Instruct 405B by 1.583.785.2+1.5
  • MATHtie74.673.8tie

Questions people ask

How do you compare the two?

We use the 13 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.