Claude 3 Haiku vs Llama 3 Instruct 70B
Wins 2 of 5 areas
Facts · Long documents
Wins 1 of 5 areas
Following instructions
Claude 3 Haiku wins more areas, narrowly.Llama 3 Instruct 70B is better at following instructions.
Scores updated · 19 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.
- FactsGetting facts right instead of making them up10Claude 3 Haiku1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3 Instruct 70B1 of 1 test
- CodingWriting and fixing software00Even0 each · 2 ties
- ReasoningHard problems that need careful thinking00Even0 each · 3 ties
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.
Claude 3 Haiku costs 56% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude 3 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7points ahead
Where Llama 3 Instruct 70B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+1points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- GPQA Diamondtie37.437.9tie
- Humanity's Last Examtie4.14.5tie
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 719.512.5+7
- AA-Omniscience · Accuracytie17.617.7tie
Following instructionsLlama 3 Instruct 70B
- IFBenchLlama 3 Instruct 70B by 136.137.1+1
Other results10 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.
- HarmBenchClaude 3 Haiku by 27.391.364+27.3
- τ²-Bench Telecom (AA run)Claude 3 Haiku by 21.121.10+21.1
- AIR-Bench 2024Claude 3 Haiku by 18.182.764.6+18.1
- XSTestLlama 3 Instruct 70B by 11.585.396.8+11.5
- AA Agentic IndexClaude 3 Haiku by 770+7
- AA-OmniscienceClaude 3 Haiku by 5.7-48.6-54.3+5.7
- anthropic_red_teamClaude 3 Haiku by 3.310096.7+3.3
- simple_safety_testsClaude 3 Haiku by 110099+1
- AA Intelligencetie5.65.5tie
- Artificial Analysis Coding Indextie6.76.8tie
Questions people ask
Which is better, Claude 3 Haiku or Llama 3 Instruct 70B?
Claude 3 Haiku wins two of the five areas where both have results: facts and long documents. Llama 3 Instruct 70B wins following instructions. They are level on coding and reasoning.
Which is better for coding?
Neither. All 2 coding tests both models report are ties.
Which is cheaper?
Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens; Llama 3 Instruct 70B costs $0.65 and $2.75. That makes Claude 3 Haiku about 56% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.