DeepSeek V4 Pro vs Qwen3.8-Flash-Next
DeepSeek V4 Pro 
Qwen3.8-Flash-Next Verdict
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 61.6.
- DeepSeek V4 Pro (max) is stronger in agents & tools, composite, instruction following, long context, maths, reasoning.
- Qwen3.8-Flash-Next is stronger in coding, knowledge, multimodal.
- Qwen3.8-Flash-Next is 2.4× cheaper ($0.230 vs $0.544 per 1M blended).
- DeepSeek V4 Pro (max) streams 1.5× faster (81 vs 55 tokens per second).
| Metric | DeepSeek V4 Pro (max) | Qwen3.8-Flash-Next |
|---|---|---|
| BenchLeader Index | 64.2 | 61.6 |
| Agents & tools score | 70.2 | 65.8 |
| Coding score | 58.8 | 71.2 |
| Composite score | 75.0 | 67.4 |
| Instruction following score | 74.3 | – |
| Knowledge score | 58.1 | 59.6 |
| Long context score | 66.6 | 66.3 |
| Maths score | 53.7 | – |
| Reasoning score | 70.9 | 63.4 |
| Multimodal score | – | 64.3 |
| Blended price $/M | $0.544 | $0.230 |
| Output speed | 81 tok/s | 55 tok/s |
| Time to first answer | 55.6 s | 39.0 s |
| Context window | 1M | 256k |
| GPQA Diamond | 89.7% | – |
| FrontierMath Tiers 1–3 | 45.3% | – |
| FrontierMath Tier 4 | 2.4% | – |
| OTIS Mock AIME | 96.7% | – |
| SWE-bench Verified (Epoch) | 77.6% | – |
| SimpleQA Verified | 47.0% | – |
| SciCode | 50.0% | – |
| WeirdML | 48.9% | – |
| ProofBench | 16.0% | – |
| LMArena WebDev | – | 1635 |
| LMArena Agent | – | -0.1 |
| LiveBench | – | 76.2% |
| LiveBench Reasoning | – | 87.4% |
| LiveBench Coding | – | 72.5% |
| LiveBench Agentic Coding | – | 61.6% |
| LiveBench Mathematics | – | 85.8% |
| LiveBench Data Analysis | – | 74.2% |
| LiveBench Language | – | 74.6% |
| LiveBench Instruction Following | – | 77.1% |
| AA Intelligence Index | 36.3 | 39.9 |
| IFBench | 76.5% | – |
| AA-LCR | 80.3% | 79.7% |
| MMMU-Pro | – | 79.8% |
| AA-Omniscience | 0.8 | -9.7 |
| Terminal-Bench Hard | 46.2% | – |
| GPQA Diamond (AA) | 92.8% | 92.3% |
| Humanity's Last Exam (AA) | 41.0% | 38.0% |
| SciCode (AA) | 51.0% | 50.6% |
| τ²-Bench Telecom (AA) | 96.2% | – |
| LiveCodeBench | 87.5% | – |
| MMLU-Pro | 87.3% | – |
| LegalBench | 80.3% | – |
| CorpFin | 61.4% | – |
| TaxEval | 72.1% | – |
| SWE-bench (Vals) | 77.4% | – |
| GPQA Diamond (Vals) | 89.4% | – |
| Vals Index | 42.9 | – |
| AIME 2026 | 96.7% | – |
| HMMT February 2026 | 93.9% | – |
| MathArena Apex | 28.1% | – |
| CritPt | 18.0% | 11.1% |
| GDPval (AA) | 49.7% | 57.4% |
| τ²-Bench Banking (AA) | 39.6% | 45.4% |
| ITBench SRE (AA) | 38.3% | – |
| Analyst Agent (AA) | 18.8% | – |
| APEX-Agents (AA) | 24.3% | – |
| CaseLaw v2 | 59.4% | – |
| Code Migration | 26.2% | – |
| Excel Modeling Benchmark | 51.6% | – |
| Finance Agent v2 | 44.1% | – |
| Harvey's Legal Agent Benchmark | 3.8% | – |
| Legal Research Bench | 23.1% | – |
| MedCode | 40.5% | – |
| MedScribe | 75.1% | – |
| ProgramBench | 0.0% | – |
| Public Benefits Bench | 62.9% | – |
| SkillsBench | 51.3% | – |
| Vibe Code Bench v1.1 | 49.9% | – |
| Chess Puzzles | 20.0% | – |
| LMCA | 41.2% | – |
| DTBench | 90.7% | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
DeepSeek V4 Pro vs Qwen3.8-Flash-Next: questions
- Is DeepSeek V4 Pro better than Qwen3.8-Flash-Next?
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 61.6. The BenchLeader Index combines every independent quality benchmark; DeepSeek V4 Pro (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is DeepSeek V4 Pro better than Qwen3.8-Flash-Next for coding?
- Qwen3.8-Flash-Next scores higher in coding (71 vs 59 on the category index, where 50 is average).
- Is DeepSeek V4 Pro better than Qwen3.8-Flash-Next for agentic tasks?
- DeepSeek V4 Pro scores higher in agentic tasks (70 vs 66 on the category index, where 50 is average).
- Which is cheaper, DeepSeek V4 Pro or Qwen3.8-Flash-Next?
- Qwen3.8-Flash-Next is cheaper: $0.230 against $0.544 per million tokens, blended at three input tokens per output token.
- Which is faster, DeepSeek V4 Pro or Qwen3.8-Flash-Next?
- DeepSeek V4 Pro streams faster: 81 against 55 output tokens per second.
- Which has the larger context window?
- DeepSeek V4 Pro accepts more context: 1M against 256k tokens.