Apertus 70B Instruct vs Claude 3.5 Haiku
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Facts · Long documents · Following instructions
Claude 3.5 Haiku is the stronger all-rounder.
Scores updated · 14 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.
- CodingWriting and fixing software02Claude 3.5 Haiku2 of 2 tests
- FactsGetting facts right instead of making them up02Claude 3.5 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts01Claude 3.5 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked01Claude 3.5 Haiku1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
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+41.7points ahead
- Code for real scientific research problemsSciCode+21.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+16.9points ahead
Where Apertus 70B Instruct pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.9points ahead
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.5 Haiku
- SciCodeClaude 3.5 Haiku by 21.75.727.4+21.7
- Terminal-Bench HardClaude 3.5 Haiku by 2.302.3+2.3
ReasoningEven
- GPQA DiamondClaude 3.5 Haiku by 13.627.240.8+13.6
- Humanity's Last ExamApertus 70B Instruct by 1.95.53.6+1.9
- CritPttie00tie
FactsClaude 3.5 Haiku
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 41.717.258.9+41.7
- AA-Omniscience · AccuracyClaude 3.5 Haiku by 1.611.613.2+1.6
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 16.925.942.8+16.9
Other results5 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 39-61.5-22.5+39
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 141.915.9+14
- τ²-Bench Telecom (AA run)Claude 3.5 Haiku by 11.712.924.6+11.7
- AA IntelligenceClaude 3.5 Haiku by 3.85.18.9+3.8
- AA Agentic IndexApertus 70B Instruct by 2.44.31.9+2.4
Questions people ask
Which is better, Apertus 70B Instruct or Claude 3.5 Haiku?
Claude 3.5 Haiku wins four of the five areas where both have results: coding, facts, long documents and following instructions. Apertus 70B Instruct wins none. They are level on reasoning.
Which is better for coding?
Claude 3.5 Haiku. It wins 2 of the 2 coding tests both models report; Apertus 70B Instruct wins none.
How do you compare the two?
We use the 14 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 5 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.