DeepSeek-V3 wins more areas, narrowly.Qwen3 30B A3B is cheaper.
Scores updated · 19 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 software20DeepSeek-V32 of 2 tests
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
- Following instructionsDoing exactly what it is asked00Even0 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 12% 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 DeepSeek-V3 pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+12.9points ahead
- Code for real scientific research problemsSciCode+10.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+9.3points ahead
Where Qwen3 30B A3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.5points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- Terminal-Bench HardDeepSeek-V3 by 12.915.22.3+12.9
- SciCodeDeepSeek-V3 by 10.53928.5+10.5
ReasoningEven
- GPQA DiamondDeepSeek-V3 by 3.965.561.6+3.9
- Humanity's Last ExamQwen3 30B A3B by 1.54.76.2+1.5
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V3 by 9.325.416.2+9.3
- AA-Omniscience · Non-hallucinationQwen3 30B A3B by 5.214.119.3+5.2
Other results9 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 30B A3B by 21.629.250.8+21.6
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 21.147.126+21.1
- AIME 2025Qwen3 30B A3B by 19.651.370.9+19.6
- LiveCodeBenchQwen3 30B A3B by 13.449.262.6+13.4
- AA-OmniscienceDeepSeek-V3 by 10.8-40.7-51.5+10.8
- Artificial Analysis Coding IndexDeepSeek-V3 by 9.72313.3+9.7
- AA IntelligenceDeepSeek-V3 by 2.19.77.6+2.1
- LiveBenchQwen3 30B A3B by 1.972.474.3+1.9
- Arena Hardtie91.491tie
Questions people ask
Which is better, DeepSeek-V3 or Qwen3 30B A3B?
DeepSeek-V3 wins two of the six areas where both have results: coding and long documents. Qwen3 30B A3B wins none, but costs 12% less. They are level on agents, reasoning, facts and following instructions.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Qwen3 30B A3B wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Qwen3 30B A3B costs $0.20 and $0.80. That makes Qwen3 30B A3B about 12% cheaper for the same work.
How do you compare the two?
We use the 19 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 9 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.