Apriel-v1.5-15B-Thinker vs Claude 3 Haiku
Wins 4 of 6 areas
Coding · Reasoning · Images and charts · Following instructions
Wins 2 of 6 areas
Facts · Long documents
Apriel-v1.5-15B-Thinker is the stronger all-rounder.Claude 3 Haiku is better at facts.
Scores updated · 13 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.
- ReasoningHard problems that need careful thinking30Apriel-v1.5-15B-Thinker3 of 3 tests
- CodingWriting and fixing software20Apriel-v1.5-15B-Thinker2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10Apriel-v1.5-15B-Thinker1 of 1 test
- Following instructionsDoing exactly what it is asked10Apriel-v1.5-15B-Thinker1 of 1 test
- FactsGetting facts right instead of making them up02Claude 3 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts01Claude 3 Haiku1 of 1 test
Images and charts, 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 three tests each model wins by the widest margin. Scores are out of 100.
Where Apriel-v1.5-15B-Thinker pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+33.9points ahead
- Harder college exam questions with imagesMMMU-Pro+26.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+25.6points ahead
Where Claude 3 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+6.4points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.1points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingApriel-v1.5-15B-Thinker
- SciCodeApriel-v1.5-15B-Thinker by 16.234.818.6+16.2
- Terminal-Bench HardApriel-v1.5-15B-Thinker by 9.810.60.8+9.8
ReasoningApriel-v1.5-15B-Thinker
- GPQA DiamondApriel-v1.5-15B-Thinker by 33.971.337.4+33.9
- Humanity's Last ExamApriel-v1.5-15B-Thinker by 812.14.1+8
- CritPtApriel-v1.5-15B-Thinker by 1.11.10+1.1
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 4.814.719.5+4.8
- AA-Omniscience · AccuracyClaude 3 Haiku by 1.116.417.6+1.1
Images and chartsApriel-v1.5-15B-Thinker
- MMMU-ProApriel-v1.5-15B-Thinker by 26.357.130.8+26.3
Following instructionsApriel-v1.5-15B-Thinker
- IFBenchApriel-v1.5-15B-Thinker by 25.661.736.1+25.6
Other results3 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.
- τ²-Bench Telecom (AA run)Apriel-v1.5-15B-Thinker by 47.368.421.1+47.3
- AA IntelligenceApriel-v1.5-15B-Thinker by 8.213.85.6+8.2
- AA-OmniscienceClaude 3 Haiku by 6.2-54.8-48.6+6.2
Questions people ask
Which is better, Apriel-v1.5-15B-Thinker or Claude 3 Haiku?
Apriel-v1.5-15B-Thinker wins four of the six areas where both have results: coding, reasoning, images and charts and following instructions. Claude 3 Haiku wins facts and long documents.
Which is better for coding?
Apriel-v1.5-15B-Thinker. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
How do you compare the two?
We use the 13 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 3 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.