Apertus 70B Instruct vs Llama 3.3 Nemotron Super 49B V1
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Llama 3.3 Nemotron Super 49B V1 is the stronger all-rounder.
Scores updated · 13 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 thinking01Llama 3.3 Nemotron Super 49B V11 of 3 tests · 2 ties
- CodingWriting and fixing software01Llama 3.3 Nemotron Super 49B V11 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Llama 3.3 Nemotron Super 49B V11 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3.3 Nemotron Super 49B V11 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 Llama 3.3 Nemotron Super 49B V1 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+37.1points ahead
- Code for real scientific research problemsSciCode+22.5points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.2points ahead
Where Apertus 70B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.2points 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.
CodingLlama 3.3 Nemotron Super 49B V1
- SciCodeLlama 3.3 Nemotron Super 49B V1 by 22.55.728.2+22.5
- Terminal-Bench Hardtie00tie
ReasoningLlama 3.3 Nemotron Super 49B V1
- GPQA DiamondLlama 3.3 Nemotron Super 49B V1 by 37.127.264.3+37.1
- Humanity's Last Examtie5.55.6tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationApertus 70B Instruct by 8.217.29+8.2
- AA-Omniscience · AccuracyLlama 3.3 Nemotron Super 49B V1 by 5.511.617.1+5.5
Long documentsLlama 3.3 Nemotron Super 49B V1
- AA-LCRLlama 3.3 Nemotron Super 49B V1 by 18.3018.3+18.3
Following instructionsLlama 3.3 Nemotron Super 49B V1
- IFBenchLlama 3.3 Nemotron Super 49B V1 by 12.225.938.1+12.2
Other results4 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)Llama 3.3 Nemotron Super 49B V1 by 1412.926.9+14
- Artificial Analysis Coding IndexLlama 3.3 Nemotron Super 49B V1 by 7.51.99.4+7.5
- AA IntelligenceLlama 3.3 Nemotron Super 49B V1 by 3.85.18.9+3.8
- AA-OmniscienceLlama 3.3 Nemotron Super 49B V1 by 3.2-61.5-58.3+3.2
Questions people ask
Which is better, Apertus 70B Instruct or Llama 3.3 Nemotron Super 49B V1?
Llama 3.3 Nemotron Super 49B V1 wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Apertus 70B Instruct wins none. They are level on facts.
Which is better for coding?
Llama 3.3 Nemotron Super 49B V1. It wins 1 of the 2 coding tests both models report; Apertus 70B Instruct wins none, and 1 is a tie.
How do you compare the two?
We use the 13 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 4 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.