Apriel-v1.6-15B-Thinker vs Tri-21B-Think
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 5 areas
—
Apriel-v1.6-15B-Thinker is the stronger all-rounder.
Scores updated · 11 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.
- ReasoningHard problems that need careful thinking20Apriel-v1.6-15B-Thinker2 of 3 tests · 1 tie
- CodingWriting and fixing software10Apriel-v1.6-15B-Thinker1 of 1 test
- Long documentsFinding answers in very long texts10Apriel-v1.6-15B-Thinker1 of 1 test
- Following instructionsDoing exactly what it is asked10Apriel-v1.6-15B-Thinker1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Coding, 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+34.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+13.6points ahead
Where Tri-21B-Think pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.5points ahead
Every test, side by side
All 11 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 13.614.40.8+13.6
ReasoningApriel-v1.6-15B-Thinker
- GPQA DiamondApriel-v1.6-15B-Thinker by 13.273.360.1+13.2
- Humanity's Last ExamApriel-v1.6-15B-Thinker by 4.910.85.9+4.9
- CritPttie0.30.3tie
FactsEven
- AA-Omniscience · Non-hallucinationTri-21B-Think by 6.58.114.6+6.5
- AA-Omniscience · AccuracyApriel-v1.6-15B-Thinker by 4.71712.3+4.7
Long documentsApriel-v1.6-15B-Thinker
- AA-LCRApriel-v1.6-15B-Thinker by 34.650.315.7+34.6
Following instructionsApriel-v1.6-15B-Thinker
- IFBenchApriel-v1.6-15B-Thinker by 14.569.154.6+14.5
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)Tri-21B-Think by 11.769.381+11.7
- AA IntelligenceApriel-v1.6-15B-Thinker by 4.413.49+4.4
- AA-OmniscienceApriel-v1.6-15B-Thinker by 3.1-59.4-62.5+3.1
Questions people ask
Which is better, Apriel-v1.6-15B-Thinker or Tri-21B-Think?
Apriel-v1.6-15B-Thinker wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Tri-21B-Think wins none. They are level on facts.
Which is better for coding?
Apriel-v1.6-15B-Thinker. It wins the one coding test both models report.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 8 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.