Phi 4 Mini Instruct vs Qwen3.5 35B A3B
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Qwen3.5 35B A3B is the stronger all-rounder.
Scores updated · 24 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.
- ReasoningHard problems that need careful thinking02Qwen3.5 35B A3B2 of 3 tests · 1 tie
- CodingWriting and fixing software02Qwen3.5 35B A3B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own02Qwen3.5 35B A3B2 of 2 tests
- FactsGetting facts right instead of making them up12Qwen3.5 35B A3B2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.5 35B A3B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 35B A3B1 of 1 test
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 Qwen3.5 35B A3B pulls ahead
- Reasons across sets of long documentsAA-LCR+56.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+51.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+51.4points ahead
Where Phi 4 Mini Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+7.4points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 35B A3B
- SciCodeQwen3.5 35B A3B by 26.910.837.7+26.9
- Terminal-Bench HardQwen3.5 35B A3B by 26.5026.5+26.5
AgentsQwen3.5 35B A3B
- GDPValQwen3.5 35B A3B by 5.605.6+5.6
- τ-Bench V3 · BankingQwen3.5 35B A3B by 3.914.9+3.9
ReasoningQwen3.5 35B A3B
- GPQA DiamondQwen3.5 35B A3B by 51.433.184.5+51.4
- Humanity's Last ExamQwen3.5 35B A3B by 16.54.521+16.5
- CritPttie00.9tie
FactsQwen3.5 35B A3B
- Vectara HHEM hallucination ratelower is betterQwen3.5 35B A3B by 1323.510.5+13
- AA-Omniscience · AccuracyQwen3.5 35B A3B by 10.69.520.1+10.6
- AA-Omniscience · Non-hallucinationPhi 4 Mini Instruct by 7.42214.6+7.4
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 51.421.172.5+51.4
Other results12 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)Qwen3.5 35B A3B by 818.289.2+81
- OpenBookQAPhi 4 Mini Instruct by 3579.244.2+35
- Artificial Analysis Coding IndexQwen3.5 35B A3B by 33.23.837+33.2
- vectara_avg_summary_lengthPhi 4 Mini Instruct by 325.3 rating points420.294.9+325.3 rating
- MMLU-ProQwen3.5 35B A3B by 32.552.885.3+32.5
- HellaSwagQwen3.5 35B A3B by 16.569.185.6+16.5
- AA IntelligenceQwen3.5 35B A3B by 136.319.3+13
- AA-OmniscienceQwen3.5 35B A3B by 13-61.1-48.1+13
- vectara_factual_consistencyQwen3.5 35B A3B by 1376.589.5+13
- WinoGrandeQwen3.5 35B A3B by 12.26779.2+12.2
- ARC-ChallengeQwen3.5 35B A3B by 11.783.795.4+11.7
- vectara_answer_rateQwen3.5 35B A3B by 7.392.599.8+7.3
Questions people ask
Which is better, Phi 4 Mini Instruct or Qwen3.5 35B A3B?
Qwen3.5 35B A3B wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Phi 4 Mini Instruct wins none.
Which is better for coding?
Qwen3.5 35B A3B. It wins 2 of the 2 coding tests both models report; Phi 4 Mini Instruct wins none.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.