Apertus 70B Instruct vs Sarvam M (Reasoning)
Wins 0 of 5 areas
—
Wins 2 of 5 areas
Coding · Following instructions
Sarvam M (Reasoning) wins more areas, narrowly.
Scores updated · 14 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 software02Sarvam M (Reasoning)2 of 2 tests
- Following instructionsDoing exactly what it is asked01Sarvam M (Reasoning)1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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 Sarvam M (Reasoning) pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+14.4points ahead
- Code for real scientific research problemsSciCode+12.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.9points ahead
Where Apertus 70B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+2.4points ahead
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingSarvam M (Reasoning)
- SciCodeSarvam M (Reasoning) by 12.15.717.8+12.1
- Terminal-Bench HardSarvam M (Reasoning) by 2.302.3+2.3
ReasoningEven
- GPQA DiamondSarvam M (Reasoning) by 14.427.241.6+14.4
- Humanity's Last ExamApertus 70B Instruct by 2.45.53.1+2.4
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationApertus 70B Instruct by 7.817.29.4+7.8
- AA-Omniscience · AccuracySarvam M (Reasoning) by 3.611.615.2+3.6
Following instructionsSarvam M (Reasoning)
- IFBenchSarvam M (Reasoning) by 5.925.931.8+5.9
Other results5 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)Apertus 70B Instruct by 12.912.90+12.9
- Artificial Analysis Coding IndexSarvam M (Reasoning) by 5.61.97.5+5.6
- AA Agentic IndexApertus 70B Instruct by 4.34.30+4.3
- AA Intelligencetie5.15.3tie
- AA-Omnisciencetie-61.5-61.6tie
Questions people ask
Which is better, Apertus 70B Instruct or Sarvam M (Reasoning)?
Sarvam M (Reasoning) wins two of the five areas where both have results: coding and following instructions. Apertus 70B Instruct wins none. They are level on reasoning, facts and long documents.
Which is better for coding?
Sarvam M (Reasoning). It wins 2 of the 2 coding tests both models report; Apertus 70B Instruct wins none.
How do you compare the two?
We use the 14 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 5 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.