GPT-4o vs Qwen3 30B A3B
Wins 3 of 6 areas
Coding · Facts · Long documents
Wins 2 of 6 areas
Reasoning · Following instructions
GPT-4o wins more areas, narrowly.Qwen3 30B A3B is cheaper and better at reasoning.
Scores updated · 18 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.
- CodingWriting and fixing software20GPT-4o2 of 2 tests
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- ReasoningHard problems that need careful thinking02Qwen3 30B A3B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Qwen3 30B A3B1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 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 95% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+42.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+7.5points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+6points ahead
Where Qwen3 30B A3B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.5points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+4.4points ahead
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-4o
- Terminal-Bench HardGPT-4o by 68.32.3+6
- SciCodeGPT-4o by 4.833.328.5+4.8
ReasoningQwen3 30B A3B
- GPQA DiamondQwen3 30B A3B by 952.661.6+9
- Humanity's Last ExamQwen3 30B A3B by 4.41.86.2+4.4
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 42.862.119.3+42.8
- AA-Omniscience · AccuracyGPT-4o by 7.523.716.2+7.5
Following instructionsQwen3 30B A3B
- IFBenchQwen3 30B A3B by 5.53641.5+5.5
Other results8 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.
- AIME 2025Qwen3 30B A3B by 59.211.770.9+59.2
- AA-OmniscienceGPT-4o by 41-10.5-51.5+41
- LiveCodeBenchQwen3 30B A3B by 24.338.362.6+24.3
- Arena HardQwen3 30B A3B by 11.779.391+11.7
- Artificial Analysis Coding IndexGPT-4o by 10.924.213.3+10.9
- τ²-Bench Telecom (AA run)GPT-4o by 2.928.926+2.9
- AA Agentic IndexGPT-4o by 18.47.4+1
- AA Intelligencetie7.37.6tie
Questions people ask
Which is better, GPT-4o or Qwen3 30B A3B?
GPT-4o wins three of the six areas where both have results: coding, facts and long documents. Qwen3 30B A3B wins reasoning and following instructions, and costs 95% less. They are level on agents.
Which is better for coding?
GPT-4o. It wins 2 of the 2 coding tests both models report; Qwen3 30B A3B wins none.
Which is cheaper?
GPT-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Qwen3 30B A3B costs $0.20 and $0.80. That makes Qwen3 30B A3B about 95% cheaper for the same work.
How do you compare the two?
We use the 18 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 8 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.