Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Llama 3 Instruct 8B vs Qwen2.5 3B

Meta · released

Alibaba · released

Scores updated · 10 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.

Llama 3 Instruct 8B$0.04 to read · $0.14 to write$0.19Price from Artificial Analysis
Qwen2.5 3BNo current price is tracked.

Every test, side by side

All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Other results10 tests
  • GSM8KQwen2.5 3B by 29.249.979.1+29.2
  • C-EvalQwen2.5 3B by 25.549.575+25.5
  • CMMLUQwen2.5 3B by 24.250.875+24.2
  • HumanEvalLlama 3 Instruct 8B by 18.360.442.1+18.3
  • TriviaQALlama 3 Instruct 8B by 16.667.751.1+16.6
  • MBPPLlama 3 Instruct 8B by 10.667.757.1+10.6
  • MMLUQwen2.5 3B by 5.460.165.6+5.4
  • MATHQwen2.5 3B by 3.539.142.6+3.5
  • BBHLlama 3 Instruct 8B by 1.457.756.3+1.4
  • MMLU-Protie35.434.6tie

Questions people ask

How do you compare the two?

We use the 10 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.