Claude 3.5 Haiku vs Llama 3.1 70B Instruct
Wins 2 of 6 areas
Long documents · Following instructions
Wins 0 of 6 areas
—
Claude 3.5 Haiku wins more areas, narrowly.
Scores updated · 26 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 documentsFinding answers in very long texts10Claude 3.5 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3.5 Haiku1 of 1 test
- CodingWriting and fixing software00Even0 each · 2 ties
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking00Even0 each · 3 ties
- FactsGetting facts right instead of making them up11Even1 each
Agents, 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37.1points ahead
- Reasons across sets of long documentsAA-LCR+19.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+8.4points ahead
Where Llama 3.1 70B Instruct pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.5points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningEven
- Humanity's Last Examtie3.64.5tie
- GPQA Diamondtie40.840.9tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 37.158.921.8+37.1
- AA-Omniscience · AccuracyLlama 3.1 70B Instruct by 6.513.219.7+6.5
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 8.442.834.4+8.4
Other results16 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.
- AA-OmniscienceClaude 3.5 Haiku by 20.6-22.5-43.1+20.6
- MATHClaude 3.5 Haiku by 19.287.268+19.2
- MMLULlama 3.1 70B Instruct by 18.967.186+18.9
- MBPPClaude 3.5 Haiku by 1785.668.6+17
- GSM8KLlama 3.1 70B Instruct by 12.381.593.8+12.3
- naturalquestions_closedbookLlama 3.1 70B Instruct by 10.834.445.2+10.8
- τ²-Bench Telecom (AA run)Claude 3.5 Haiku by 9.424.615.2+9.4
- OpenBookQALlama 3.1 70B Instruct by 8.485.493.8+8.4
- HumanEvalClaude 3.5 Haiku by 7.688.180.5+7.6
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 515.910.9+5
- DROPClaude 3.5 Haiku by 3.583.179.6+3.5
- AA Agentic IndexLlama 3.1 70B Instruct by 3.21.95.1+3.2
- AA IntelligenceClaude 3.5 Haiku by 2.38.96.6+2.3
- MMLU-ProLlama 3.1 70B Instruct by 1.46566.4+1.4
- MGSMLlama 3.1 70B Instruct by 1.385.686.9+1.3
- NarrativeQAtie76.377.2tie
Questions people ask
Which is better, Claude 3.5 Haiku or Llama 3.1 70B Instruct?
Claude 3.5 Haiku wins two of the six areas where both have results: long documents and following instructions. Llama 3.1 70B Instruct wins none. They are level on coding, agents, reasoning and facts.
Which is better for coding?
Neither. All 2 coding tests both models report are ties.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.