DeepSeek V4 Pro vs Gemini 3.8 Flash
DeepSeek V4 Pro 
Gemini 3.8 Flash Verdict
- DeepSeek V4 Pro (max) and Gemini 3.8 Flash (medium) are level on quality (64.2 vs 64.9).
- DeepSeek V4 Pro (max) is stronger in instruction following, maths, reasoning.
- Gemini 3.8 Flash (medium) is stronger in agents & tools, coding, composite, knowledge, long context, multimodal.
- DeepSeek V4 Pro (max) is 2.8× cheaper ($0.544 vs $1.50 per 1M blended).
| Metric | DeepSeek V4 Pro (max) | Gemini 3.8 Flash (medium) |
|---|---|---|
| BenchLeader Index | 64.2 | 64.9 |
| Agents & tools score | 70.2 | 74.8 |
| Coding score | 58.8 | 63.8 |
| Composite score | 75.0 | 79.7 |
| Instruction following score | 74.3 | – |
| Knowledge score | 58.1 | 77.8 |
| Long context score | 66.6 | 68.5 |
| Maths score | 53.7 | – |
| Reasoning score | 70.9 | 65.6 |
| Multimodal score | – | 68.9 |
| Blended price $/M | $0.544 | $1.50 |
| Output speed | 81 tok/s | 78 tok/s |
| Time to first answer | 55.6 s | 2.3 s |
| Context window | 1M | 1.0M |
| 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% | 54.4% |
| WeirdML | 48.9% | – |
| ProofBench | 16.0% | – |
| AA Intelligence Index | 36.3 | 40 |
| IFBench | 76.5% | – |
| AA-LCR | 80.3% | 84.0% |
| MMMU-Pro | – | 84.2% |
| AA-Omniscience | 0.8 | 28.6 |
| Terminal-Bench Hard | 46.2% | – |
| GPQA Diamond (AA) | 92.8% | 93.5% |
| Humanity's Last Exam (AA) | 41.0% | 42.1% |
| SciCode (AA) | 51.0% | 55.1% |
| 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% | 12.3% |
| GDPval (AA) | 49.7% | 47.8% |
| τ²-Bench Banking (AA) | 39.6% | 45.8% |
| 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% | – |
| DeepSWE | – | 71.0% |
| LMCA | 41.2% | – |
| DTBench | 90.7% | – |
| CursorBench | – | 67.0% |
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 Gemini 3.8 Flash: questions
- Is DeepSeek V4 Pro better than Gemini 3.8 Flash?
- DeepSeek V4 Pro (max) and Gemini 3.8 Flash (medium) are level on quality (64.2 vs 64.9). The BenchLeader Index combines every independent quality benchmark; Gemini 3.8 Flash (medium) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is DeepSeek V4 Pro better than Gemini 3.8 Flash for coding?
- Gemini 3.8 Flash scores higher in coding (64 vs 59 on the category index, where 50 is average).
- Is DeepSeek V4 Pro better than Gemini 3.8 Flash for agentic tasks?
- Gemini 3.8 Flash scores higher in agentic tasks (75 vs 70 on the category index, where 50 is average).
- Which is cheaper, DeepSeek V4 Pro or Gemini 3.8 Flash?
- DeepSeek V4 Pro is cheaper: $0.544 against $1.50 per million tokens, blended at three input tokens per output token.
- Which is faster, DeepSeek V4 Pro or Gemini 3.8 Flash?
- DeepSeek V4 Pro streams faster: 81 against 78 output tokens per second.
- Which has the larger context window?
- Gemini 3.8 Flash accepts more context: 1.0M against 1M tokens.