DeepSeek-V3 wins more areas, narrowly.
Scores updated · 30 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 software30DeepSeek-V33 of 3 tests
- ReasoningHard problems that need careful thinking10DeepSeek-V31 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 3 ties
- FactsGetting facts right instead of making them up11Even1 each · 1 tie
- Following instructionsDoing exactly what it is asked00Even0 each · 1 tie
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.
DeepSeek-V3 costs 35% 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
- Command-line tasks in a real terminalTerminal-Bench 2.1+12points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+11.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+10.2points ahead
Where Qwen3 14B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.1points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- Terminal-Bench 2.1DeepSeek-V3 by 1216.94.9+12
- Terminal-Bench HardDeepSeek-V3 by 11.415.23.8+11.4
- SciCodeDeepSeek-V3 by 8.33930.7+8.3
AgentsEven
- τ-Bench V3 · Bankingtie4.75.6tie
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 5.165.560.4+5.1
- Humanity's Last Examtie4.74.5tie
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V3 by 10.225.415.3+10.2
- AA-Omniscience · Non-hallucinationQwen3 14B by 10.114.124.2+10.1
- Vectara HHEM hallucination ratelower is bettertie6.15.4tie
Other results16 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.
- Arena HardDeepSeek-V3 by 48.791.442.7+48.7
- AIME 2024Qwen3 14B by 44.539.283.7+44.5
- AIME 2025Qwen3 14B by 19.151.370.4+19.1
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 12.647.134.5+12.6
- LiveCodeBenchQwen3 14B by 10.149.259.3+10.1
- Artificial Analysis Coding IndexDeepSeek-V3 by 9.22313.8+9.2
- AA-OmniscienceDeepSeek-V3 by 8.2-40.7-49+8.2
- MATH-500 (EM)Qwen3 14B by 6.690.296.8+6.6
- ZebraLogicQwen3 14B by 4.58488.5+4.5
- vectara_avg_summary_lengthQwen3 14B by 29.4 rating points81.7111.1+29.4 rating
- vectara_answer_rateQwen3 14B by 2.497.599.9+2.4
- AA IntelligenceDeepSeek-V3 by 1.59.78.2+1.5
- vectara_factual_consistencytie93.994.6tie
- MMLU-Reduxtie89.188.6tie
- AutoLogitie88.989.2tie
- C-Evaltie86.586.2tie
Questions people ask
Which is better, DeepSeek-V3 or Qwen3 14B?
DeepSeek-V3 wins three of the six areas where both have results: coding, reasoning and long documents. Qwen3 14B wins none. They are level on agents, facts and following instructions.
Which is better for coding?
DeepSeek-V3. It wins 3 of the 3 coding tests both models report; Qwen3 14B wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Qwen3 14B costs $0.35 and $1.40. That makes DeepSeek-V3 about 35% cheaper for the same work.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.