DeepSeek-V4.1-Flash vs Qwen3.8 Max Preview
Wins 2 of 8 areas
Coding · Long documents
Wins 5 of 8 areas
Agents · Reasoning · Facts · Images and charts · Following instructions
Qwen3.8 Max Preview is the stronger all-rounder.DeepSeek-V4.1-Flash is cheaper and better at coding.
Scores updated · 35 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- Images and chartsUnderstanding pictures, charts and video02Qwen3.8 Max Preview2 of 2 tests
- ReasoningHard problems that need careful thinking12Qwen3.8 Max Preview2 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own12Qwen3.8 Max Preview2 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.8 Max Preview2 of 3 tests
- Following instructionsDoing exactly what it is asked01Qwen3.8 Max Preview1 of 1 test
- CodingWriting and fixing software41DeepSeek-V4.1-Flash4 of 5 tests
- Long documentsFinding answers in very long texts10DeepSeek-V4.1-Flash1 of 1 test
- MathCompetition and research-level math11Even1 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-V4.1-Flash costs 81% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.8 Max Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+67.7points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+5.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+4.4points ahead
Where DeepSeek-V4.1-Flash pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+14.7points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+12.6points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+7.1points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V4.1-Flash
- LiveBench · Agentic CodingDeepSeek-V4.1-Flash by 12.677.364.7+12.6
- LiveBench · CodingDeepSeek-V4.1-Flash by 7.18072.9+7.1
- LMArena · WebDevQwen3.8 Max Preview by 49 rating points16211670+49 rating
- SciCodeDeepSeek-V4.1-Flash by 3.855.952.1+3.8
- Terminal-Bench 2.1DeepSeek-V4.1-Flash by 1.890.688.8+1.8
AgentsQwen3.8 Max Preview
- AA IT-Bench SREDeepSeek-V4.1-Flash by 6.646.940.3+6.6
- Terminal-Bench 4.0Qwen3.8 Max Preview by 5.133.838.9+5.1
- GDPValQwen3.8 Max Preview by 3.35558.3+3.3
ReasoningQwen3.8 Max Preview
- CritPtDeepSeek-V4.1-Flash by 6.32417.7+6.3
- GPQA DiamondQwen3.8 Max Preview by 1.990.992.8+1.9
- LiveBench · ReasoningQwen3.8 Max Preview by 1.586.788.2+1.5
- Humanity's Last Examtie43.343.1tie
FactsQwen3.8 Max Preview
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 67.73.571.2+67.7
- AA-Omniscience · AccuracyDeepSeek-V4.1-Flash by 14.746.431.7+14.7
- SimpleQA VerifiedQwen3.8 Max Preview by 4.442.947.3+4.4
Images and chartsQwen3.8 Max Preview
- LMArena · VisionQwen3.8 Max Preview by 33 rating points12791312+33 rating
- MMMU-ProQwen3.8 Max Preview by 2.280.682.8+2.2
MathEven
- FrontierMath Tiers 1-3 (v2)Qwen3.8 Max Preview by 3.571.274.7+3.5
- LiveBench · MathematicsDeepSeek-V4.1-Flash by 293.391.3+2
- FrontierMath Tier 4tie46.346.3tie
Long documentsDeepSeek-V4.1-Flash
- AA-LCRDeepSeek-V4.1-Flash by 2.482.780.3+2.4
Following instructionsQwen3.8 Max Preview
- LiveBench · Instruction FollowingQwen3.8 Max Preview by 4.17074.1+4.1
Other results13 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.
- Agents' Last ExamQwen3.8 Max Preview by 20.631.852.4+20.6
- DeepSWE 1.1DeepSeek-V4.1-Flash by 17.674.256.6+17.6
- AA-OmniscienceQwen3.8 Max Preview by 17.3-5.312+17.3
- CyberGymDeepSeek-V4.1-Flash by 9.688.178.5+9.6
- NL2RepoDeepSeek-V4.1-Flash by 8.16455.9+8.1
- HLE (with tools)DeepSeek-V4.1-Flash by 7.763.956.2+7.7
- AA IntelligenceQwen3.8 Max Preview by 5.939.545.4+5.9
- GDP (Surge AI)Qwen3.8 Max Preview by 5.617.222.8+5.6
- CritPt v2 HardQwen3.8 Max Preview by 4.52529.5+4.5
- livebench_languageDeepSeek-V4.1-Flash by 1.581.279.7+1.5
- HLE-DiamondDeepSeek-V4.1-Flash by 1.325.324+1.3
- Terminal-Bench-Science 0.1DeepSeek-V4.1-Flash by 112.911.9+1
- livebench_data_analysistie79.378.4tie
Questions people ask
Which is better, DeepSeek-V4.1-Flash or Qwen3.8 Max Preview?
Qwen3.8 Max Preview wins five of the eight areas we test: agents, reasoning, facts, images and charts and following instructions. DeepSeek-V4.1-Flash wins coding and long documents, and costs 81% less. They are level on math.
Which is better for coding?
DeepSeek-V4.1-Flash. It wins 4 of the 5 coding tests both models report; Qwen3.8 Max Preview wins 1.
Which is cheaper?
DeepSeek-V4.1-Flash costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes DeepSeek-V4.1-Flash about 81% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.