DeepSeek-V4-Flash vs Qwen2.5 Instruct 72B
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 5 areas
—
DeepSeek-V4-Flash is the stronger all-rounder.Qwen2.5 Instruct 72B is cheaper.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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-V4-Flash3 of 3 tests
- ReasoningHard problems that need careful thinking30DeepSeek-V4-Flash3 of 3 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4-Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Flash1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Qwen2.5 Instruct 72B costs 45% 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-Flash pulls ahead
- Reasons across sets of long documentsAA-LCR+59.7points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+55.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+42.3points ahead
Where Qwen2.5 Instruct 72B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.2points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4-Flash
- SWE-bench VerifiedDeepSeek-V4-Flash by 55.27923.8+55.2
- Terminal-Bench HardDeepSeek-V4-Flash by 31.135.64.5+31.1
- SciCodeDeepSeek-V4-Flash by 23.650.326.7+23.6
ReasoningDeepSeek-V4-Flash
- GPQA DiamondDeepSeek-V4-Flash by 41.790.849.1+41.7
- Humanity's Last ExamDeepSeek-V4-Flash by 3538.63.6+35
- CritPtDeepSeek-V4-Flash by 16.616.60+16.6
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V4-Flash by 22.940.417.5+22.9
- AA-Omniscience · Non-hallucinationQwen2.5 Instruct 72B by 6.28.314.5+6.2
Long documentsDeepSeek-V4-Flash
- AA-LCRDeepSeek-V4-Flash by 59.779.720+59.7
Following instructionsDeepSeek-V4-Flash
- IFBenchDeepSeek-V4-Flash by 42.379.236.9+42.3
Other results7 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-Flash by 60.59534.5+60.5
- Artificial Analysis Coding IndexDeepSeek-V4-Flash by 57.269.111.9+57.2
- AA-OmniscienceDeepSeek-V4-Flash by 38.8-14.3-53.1+38.8
- LiveCodeBenchDeepSeek-V4-Flash by 36.191.655.5+36.1
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V4-Flash by 30.578.948.4+30.5
- AA IntelligenceDeepSeek-V4-Flash by 26.634.37.7+26.6
- MMLU-ProDeepSeek-V4-Flash by 15.186.271.1+15.1
Questions people ask
Which is better, DeepSeek-V4-Flash or Qwen2.5 Instruct 72B?
DeepSeek-V4-Flash wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Qwen2.5 Instruct 72B wins none, but costs 45% less. They are level on facts.
Which is better for coding?
DeepSeek-V4-Flash. It wins 3 of the 3 coding tests both models report; Qwen2.5 Instruct 72B wins none.
Which is cheaper?
DeepSeek-V4-Flash costs $0.44 per million input tokens and $1.32 per million output tokens; Qwen2.5 Instruct 72B costs $0.47 and $0.49. That makes Qwen2.5 Instruct 72B about 45% cheaper for the same work.
How do you compare the two?
We use the 17 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 7 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.