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

Llama 3.1 Instruct 405B vs Qwen2.5 Instruct 72B

Meta · released

Wins 4 of 5 areas

Coding · Reasoning · Facts · Following instructions

Alibaba · released

Wins 0 of 5 areas

—

Llama 3.1 Instruct 405B is the stronger all-rounder.

Scores updated · 89 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.

Following instructions rests on a single test.

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 Instruct 405BNo current price is tracked.
Qwen2.5 Instruct 72B$0.47 to read · $0.49 to write$0.97Price from Artificial Analysis

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 Instruct 405B pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33.1points aheadLlama 3.1 Instruct 405B47.6Qwen2.5 Instruct 72B14.5
  • Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.7points aheadLlama 3.1 Instruct 405B23.2Qwen2.5 Instruct 72B17.5
  • Reasons across sets of long documentsAA-LCR+5.3points aheadLlama 3.1 Instruct 405B25.3Qwen2.5 Instruct 72B20

Where Qwen2.5 Instruct 72B pulls ahead

  • Questions about very long textsLongBench v2+3.3points aheadQwen2.5 Instruct 72B39.4Llama 3.1 Instruct 405B36.1

Every test, side by side

All 89 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingLlama 3.1 Instruct 405B

Full coding ranking

ReasoningLlama 3.1 Instruct 405B

Full reasoning ranking

FactsLlama 3.1 Instruct 405B

Full facts ranking

Long documentsEven
  • AA-LCRLlama 3.1 Instruct 405B by 5.325.320+5.3
  • LongBench v2Qwen2.5 Instruct 72B by 3.336.139.4+3.3

Full long documents ranking

Following instructionsLlama 3.1 Instruct 405B
  • IFBenchLlama 3.1 Instruct 405B by 2.13936.9+2.1

Full following instructions ranking

Other results78 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 Instruct 405B or Qwen2.5 Instruct 72B?

Llama 3.1 Instruct 405B wins four of the five areas where both have results: coding, reasoning, facts and following instructions. Qwen2.5 Instruct 72B wins none. They are level on long documents.

Which is better for coding?

Llama 3.1 Instruct 405B. It wins 2 of the 3 coding tests both models report; Qwen2.5 Instruct 72B wins none, and 1 is a tie.

How do you compare the two?

We use the 89 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 78 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.

Compare Llama 3.1 Instruct 405B with

Meta

Across the field

Compare Qwen2.5 Instruct 72B with

Alibaba

Across the field

All comparisons