Qwen3 235B A22B vs Qwen3 30B A3B
Wins 4 of 6 areas
Coding · Agents · Reasoning · Facts
Wins 1 of 6 areas
Following instructions
Qwen3 235B A22B is the stronger all-rounder.Qwen3 30B A3B is cheaper and better at following instructions.
Scores updated · 21 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 thinking20Qwen3 235B A22B2 of 3 tests · 1 tie
- CodingWriting and fixing software20Qwen3 235B A22B2 of 2 tests
- FactsGetting facts right instead of making them up20Qwen3 235B A22B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Qwen3 235B A22B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 30B A3B1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Agents, 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 costs 71% 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 235B A22B pulls ahead
- Code for real scientific research problemsSciCode+11.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.4points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+4.8points ahead
Where Qwen3 30B A3B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.8points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 235B A22B
- SciCodeQwen3 235B A22B by 11.439.928.5+11.4
- Terminal-Bench HardQwen3 235B A22B by 3.86.12.3+3.8
ReasoningQwen3 235B A22B
- GPQA DiamondQwen3 235B A22B by 8.47061.6+8.4
- Humanity's Last ExamQwen3 235B A22B by 4.8116.2+4.8
- CritPttie00tie
FactsQwen3 235B A22B
- AA-Omniscience · Non-hallucinationQwen3 235B A22B by 3.122.419.3+3.1
- AA-Omniscience · AccuracyQwen3 235B A22B by 2.318.516.2+2.3
Following instructionsQwen3 30B A3B
- IFBenchQwen3 30B A3B by 2.838.741.5+2.8
Other results11 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.
- HMMT Feb. 2025Qwen3 235B A22B by 11.762.550.8+11.7
- AA Agentic IndexQwen3 235B A22B by 1118.47.4+11
- AIME 2025Qwen3 235B A22B by 10.681.570.9+10.6
- LiveCodeBenchQwen3 235B A22B by 8.170.762.6+8.1
- AA-OmniscienceQwen3 235B A22B by 6.8-44.7-51.5+6.8
- Arena HardQwen3 235B A22B by 4.695.691+4.6
- Artificial Analysis Coding IndexQwen3 235B A22B by 4.117.413.3+4.1
- LiveBenchQwen3 235B A22B by 2.877.174.3+2.8
- τ²-Bench Telecom (AA run)Qwen3 30B A3B by 22426+2
- AA IntelligenceQwen3 235B A22B by 1.99.57.6+1.9
- BFCLv4Qwen3 235B A22B by 1.770.869.1+1.7
Questions people ask
Which is better, Qwen3 235B A22B or Qwen3 30B A3B?
Qwen3 235B A22B wins four of the six areas where both have results: coding, agents, reasoning and facts. Qwen3 30B A3B wins following instructions, and costs 71% less. They are level on long documents.
Which is better for coding?
Qwen3 235B A22B. It wins 2 of the 2 coding tests both models report; Qwen3 30B A3B wins none.
Which is cheaper?
Qwen3 235B A22B costs $0.70 per million input tokens and $2.80 per million output tokens; Qwen3 30B A3B costs $0.20 and $0.80. That makes Qwen3 30B A3B about 71% cheaper for the same work.
How do you compare the two?
We use the 21 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 11 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.