DeepSeek-V4-Pro vs Qwen3 4B 2507 Thinking
Wins 5 of 6 areas
Coding · Reasoning · Math · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-V4-Pro is the stronger all-rounder.Qwen3 4B 2507 Thinking is cheaper.
Scores updated · 13 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 thinking30DeepSeek-V4-Pro3 of 3 tests
- MathCompetition and research-level math20DeepSeek-V4-Pro2 of 2 tests
- CodingWriting and fixing software10DeepSeek-V4-Pro1 of 1 test
- Long documentsFinding answers in very long texts10DeepSeek-V4-Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Pro1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Coding, 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 4B 2507 Thinking costs 97% 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-V4-Pro pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+44.7points ahead
- Harvard-MIT high-school math contest problemsHMMT Feb. 2026+42.2points ahead
- Reasons across sets of long documentsAA-LCR+37.4points ahead
Where Qwen3 4B 2507 Thinking pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.9points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningDeepSeek-V4-Pro
- Humanity's Last ExamDeepSeek-V4-Pro by 31.337.56.2+31.3
- GPQA DiamondDeepSeek-V4-Pro by 22.188.866.7+22.1
- CritPtDeepSeek-V4-Pro by 12.912.90+12.9
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V4-Pro by 30.54312.5+30.5
- AA-Omniscience · Non-hallucinationQwen3 4B 2507 Thinking by 10.95.916.8+10.9
MathDeepSeek-V4-Pro
- HMMT Feb. 2026DeepSeek-V4-Pro by 42.295.253+42.2
- AIME 2026DeepSeek-V4-Pro by 14.296.782.5+14.2
Following instructionsDeepSeek-V4-Pro
- IFBenchDeepSeek-V4-Pro by 26.776.549.8+26.7
Other results3 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)DeepSeek-V4-Pro by 70.896.225.4+70.8
- AA-OmniscienceDeepSeek-V4-Pro by 49.6-10.7-60.3+49.6
- AA IntelligenceDeepSeek-V4-Pro by 21.630.48.8+21.6
Questions people ask
Which is better, DeepSeek-V4-Pro or Qwen3 4B 2507 Thinking?
DeepSeek-V4-Pro wins five of the six areas where both have results: coding, reasoning, math, long documents and following instructions. Qwen3 4B 2507 Thinking wins none, but costs 97% less. They are level on facts.
Which is better for coding?
DeepSeek-V4-Pro. It wins the one coding test both models report.
Which is cheaper?
DeepSeek-V4-Pro costs $0.43 per million input tokens and $0.87 per million output tokens; Qwen3 4B 2507 Thinking costs $0.01 and $0.03. That makes Qwen3 4B 2507 Thinking about 97% cheaper for the same work.
How do you compare the two?
We use the 13 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 3 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.