Apertus 70B Instruct vs Qwen3 30B A3B 2507 Instruct
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Qwen3 30B A3B 2507 Instruct 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 thinking02Qwen3 30B A3B 2507 Instruct2 of 3 tests · 1 tie
- CodingWriting and fixing software01Qwen3 30B A3B 2507 Instruct1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3 30B A3B 2507 Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 30B A3B 2507 Instruct1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Coding, 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.
Qwen3 30B A3B 2507 Instruct costs 73% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3 30B A3B 2507 Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+38.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.4points ahead
Where Apertus 70B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.6points 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.
CodingQwen3 30B A3B 2507 Instruct
- Terminal-Bench HardQwen3 30B A3B 2507 Instruct by 6.106.1+6.1
ReasoningQwen3 30B A3B 2507 Instruct
- GPQA DiamondQwen3 30B A3B 2507 Instruct by 38.727.265.9+38.7
- Humanity's Last ExamQwen3 30B A3B 2507 Instruct by 1.45.56.9+1.4
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationApertus 70B Instruct by 12.617.24.6+12.6
- AA-Omniscience · AccuracyQwen3 30B A3B 2507 Instruct by 3.411.615+3.4
Long documentsQwen3 30B A3B 2507 Instruct
- AA-LCRQwen3 30B A3B 2507 Instruct by 26.3026.3+26.3
Following instructionsQwen3 30B A3B 2507 Instruct
- IFBenchQwen3 30B A3B 2507 Instruct by 7.225.933.1+7.2
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-OmniscienceApertus 70B Instruct by 4.6-61.5-66.2+4.6
- τ²-Bench Telecom (AA run)Apertus 70B Instruct by 2.712.910.2+2.7
- AA IntelligenceQwen3 30B A3B 2507 Instruct by 2.45.17.5+2.4
Questions people ask
Which is better, Apertus 70B Instruct or Qwen3 30B A3B 2507 Instruct?
Qwen3 30B A3B 2507 Instruct 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?
Qwen3 30B A3B 2507 Instruct. It wins the one coding test both models report.
Which is cheaper?
Apertus 70B Instruct costs $0.82 per million input tokens and $2.92 per million output tokens; Qwen3 30B A3B 2507 Instruct costs $0.20 and $0.80. That makes Qwen3 30B A3B 2507 Instruct about 73% cheaper for the same work.
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.