Apriel-v1.5-15B-Thinker vs Claude 3.7 Sonnet
Wins 1 of 6 areas
Following instructions
Wins 4 of 6 areas
Coding · Facts · Images and charts · Long documents
Claude 3.7 Sonnet is the stronger all-rounder.Apriel-v1.5-15B-Thinker is better at following instructions.
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.
- CodingWriting and fixing software02Claude 3.7 Sonnet2 of 2 tests
- FactsGetting facts right instead of making them up02Claude 3.7 Sonnet2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video01Claude 3.7 Sonnet1 of 1 test
- Long documentsFinding answers in very long texts01Claude 3.7 Sonnet1 of 1 test
- Following instructionsDoing exactly what it is asked10Apriel-v1.5-15B-Thinker1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+45.3points ahead
- Reasons across sets of long documentsAA-LCR+30.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+11.5points ahead
Where Apriel-v1.5-15B-Thinker pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+13.4points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.4points 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.
CodingClaude 3.7 Sonnet
- Terminal-Bench HardClaude 3.7 Sonnet by 10.610.621.2+10.6
- SciCodeClaude 3.7 Sonnet by 5.534.840.3+5.5
ReasoningEven
- GPQA DiamondClaude 3.7 Sonnet by 5.971.377.2+5.9
- Humanity's Last ExamApriel-v1.5-15B-Thinker by 2.412.19.7+2.4
- CritPttie1.10.9tie
FactsClaude 3.7 Sonnet
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 45.314.760+45.3
- AA-Omniscience · AccuracyClaude 3.7 Sonnet by 11.516.428+11.5
Images and chartsClaude 3.7 Sonnet
- MMMU-ProClaude 3.7 Sonnet by 357.160.1+3
Long documentsClaude 3.7 Sonnet
- AA-LCRClaude 3.7 Sonnet by 30.421.351.7+30.4
Following instructionsApriel-v1.5-15B-Thinker
- IFBenchApriel-v1.5-15B-Thinker by 13.461.748.3+13.4
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-OmniscienceClaude 3.7 Sonnet by 54.1-54.8-0.7+54.1
- τ²-Bench Telecom (AA run)Apriel-v1.5-15B-Thinker by 13.768.454.7+13.7
- AA IntelligenceClaude 3.7 Sonnet by 3.913.817.7+3.9
Questions people ask
Which is better, Apriel-v1.5-15B-Thinker or Claude 3.7 Sonnet?
Claude 3.7 Sonnet wins four of the six areas where both have results: coding, facts, images and charts and long documents. Apriel-v1.5-15B-Thinker wins following instructions. They are level on reasoning.
Which is better for coding?
Claude 3.7 Sonnet. 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 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.