Apriel-v1.5-15B-Thinker vs Apriel-v1.6-15B-Thinker
Wins 1 of 5 areas
Facts
Wins 3 of 5 areas
Coding · Long documents · Following instructions
Apriel-v1.6-15B-Thinker is the stronger all-rounder.Apriel-v1.5-15B-Thinker is better at facts.
Scores updated · 12 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 software02Apriel-v1.6-15B-Thinker2 of 2 tests
- Long documentsFinding answers in very long texts01Apriel-v1.6-15B-Thinker1 of 1 test
- Following instructionsDoing exactly what it is asked01Apriel-v1.6-15B-Thinker1 of 1 test
- FactsGetting facts right instead of making them up10Apriel-v1.5-15B-Thinker1 of 2 tests · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Long documents and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Apriel-v1.6-15B-Thinker pulls ahead
- Reasons across sets of long documentsAA-LCR+29points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+3.8points ahead
Where Apriel-v1.5-15B-Thinker pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.3points ahead
Every test, side by side
All 12 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingApriel-v1.6-15B-Thinker
- Terminal-Bench HardApriel-v1.6-15B-Thinker by 3.810.614.4+3.8
- SciCodeApriel-v1.6-15B-Thinker by 2.534.837.3+2.5
ReasoningEven
- GPQA DiamondApriel-v1.6-15B-Thinker by 271.373.3+2
- Humanity's Last ExamApriel-v1.5-15B-Thinker by 1.312.110.8+1.3
- CritPttie1.10.3tie
FactsApriel-v1.5-15B-Thinker
- AA-Omniscience · Non-hallucinationApriel-v1.5-15B-Thinker by 6.614.78.1+6.6
- AA-Omniscience · Accuracytie16.417tie
Long documentsApriel-v1.6-15B-Thinker
- AA-LCRApriel-v1.6-15B-Thinker by 2921.350.3+29
Following instructionsApriel-v1.6-15B-Thinker
- IFBenchApriel-v1.6-15B-Thinker by 7.461.769.1+7.4
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.
- AA-OmniscienceApriel-v1.5-15B-Thinker by 4.6-54.8-59.4+4.6
- τ²-Bench Telecom (AA run)tie68.469.3tie
- AA Intelligencetie13.813.4tie
Questions people ask
Which is better, Apriel-v1.5-15B-Thinker or Apriel-v1.6-15B-Thinker?
Apriel-v1.6-15B-Thinker wins three of the five areas where both have results: coding, long documents and following instructions. Apriel-v1.5-15B-Thinker wins facts. They are level on reasoning.
Which is better for coding?
Apriel-v1.6-15B-Thinker. It wins 2 of the 2 coding tests both models report; Apriel-v1.5-15B-Thinker wins none.
How do you compare the two?
We use the 12 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 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.