# DeepSeek V4 Pro vs Gemini 3.8 Flash

> Side-by-side benchmark comparison for DeepSeek V4 Pro and Gemini 3.8 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-vs-gemini-3-8-flash
- Last updated: November 21, 2026

- Shared sourced benchmarks: 14
- HTML indexing: indexable
- Ranking lane: BenchAlign v6.0

## Quick Verdict

Pick Gemini 3.8 Flash if you want the stronger benchmark profile. DeepSeek V4 Pro only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Gemini 3.8 Flash leads overall 67.9 to 61.6.
- The clearest category separation is in knowledge, where the averages are 59.7 for DeepSeek V4 Pro and 71.5 for Gemini 3.8 Flash.
- The biggest single benchmark swing is ARC-AGI-2 in Reasoning, with scores of 61.3% and 89.2%.
- Gemini 3.8 Flash is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | DeepSeek V4 Pro | Gemini 3.8 Flash |
|----------|----------|----------|
| Creator | DeepSeek | Google |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 61.6 | 67.9 |
| Benchmarks Covered | 46 | 37 |
| Pricing (input/output) | $1.32 / $3.96 | $0.75 / $3.75 |

## Category Breakdown

### Agentic

- Winner: Gemini 3.8 Flash
- DeepSeek V4 Pro public-lane score: 60 (Supported · #55/182)
- Gemini 3.8 Flash public-lane score: 66 (Supported · #31/182)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 52.74% | 66.98% | Gemini 3.8 Flash |
| Terminal-Bench 4.1 | 6.70% | 18.20% | Gemini 3.8 Flash |
| Finch | 67.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | 89.4% | Gemini 3.8 Flash |
| BrowseComp | 83.4% | Coming soon | Coming soon |
| HLE w/ tools | 60.0% | Coming soon | Coming soon |
| MCP Atlas | 73.6% | Coming soon | Coming soon |
| Toolathlon | 51.8% | Coming soon | Coming soon |
| CyberGym | 83.3% | Coming soon | Coming soon |
| Toolathlon-Verified | 74.1% | Coming soon | Coming soon |
| Agents' Last Exam | 25.7% | Coming soon | Coming soon |
| AutomationBench | 31.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 54.7% | 81.3% | Gemini 3.8 Flash |
| Finance Agent v2 | Coming soon | 61.4% | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 19.10% | Coming soon |
| OSWorld 2.0 | Coming soon | 59.0% | Coming soon |
| ApprenticeBench | Coming soon | 24% | Coming soon |
| Hermes Index | Coming soon | 38.1% | Coming soon |
| Hermes Bench | Coming soon | 62.2% | Coming soon |
| MazeBench | Coming soon | 4% | Coming soon |

### Coding

- Winner: Gemini 3.8 Flash
- DeepSeek V4 Pro public-lane score: 59.6 (Supported · #56/180)
- Gemini 3.8 Flash public-lane score: 65.5 (Supported · #36/180)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 93.5% | Coming soon | Coming soon |
| Codeforces | 3206.0 | Coming soon | Coming soon |
| SWE-bench Verified | 80.6% | Coming soon | Coming soon |
| SWE-bench Pro | 55.4% | Coming soon | Coming soon |
| SWE Multilingual | 76.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Vibe Code Bench | 49.93% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | 89.4% | Gemini 3.8 Flash |
| NL2Repo | 61.5% | Coming soon | Coming soon |
| DeepSWE | 62.7% | 73.8% | Gemini 3.8 Flash |
| DSBench-FullStack | 71.1% | Coming soon | Coming soon |
| DSBench-Hard | 67.2% | Coming soon | Coming soon |
| OpenHarmony Bench v1.0 | 59.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | 89.5% | Gemini 3.8 Flash |
| SWE-bench (Vals) | 96.4% | 80.0% | DeepSeek V4 Pro |
| ScarfBench | Coming soon | 66.0% | Coming soon |
| CursorBench 3.2 | Coming soon | 69.2% | Coming soon |
| FrontierSWE v2 | Coming soon | 19.6% | Coming soon |
| Bug Hunt Bench | Coming soon | 18.0 fixes | Coming soon |

### Reasoning

- Winner: Gemini 3.8 Flash
- DeepSeek V4 Pro public-lane score: 64.6 (Supported · #32/161)
- Gemini 3.8 Flash public-lane score: 69.3 (Supported · #24/161)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 83.5% | Coming soon | Coming soon |
| CorpusQA 1M | 62.0% | Coming soon | Coming soon |
| ARC-AGI-1 | 90.00% | 98.50% | Gemini 3.8 Flash |
| ARC-AGI-2 | 61.3% | 89.2% | Gemini 3.8 Flash |
| ARC-AGI-3 | Coming soon | 10.4% | Coming soon |
| ARC-AGI-3 Provider Adapter | Coming soon | 35.00% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 60.7 (Estimated · #54/119)
- Gemini 3.8 Flash public-lane score: 66.8 (Supported · #23/119)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| ParseBench-2 | Coming soon | 76.67% | Coming soon |
| ExtractBench (LlamaIndex) | Coming soon | 80.71% | Coming soon |
| ParseBench-1 | Coming soon | 71.20% | Coming soon |
| CharXiv w/o tools | Coming soon | 86.2% | Coming soon |
| LVBench | Coming soon | 87.1% | Coming soon |

### Knowledge

- Winner: Gemini 3.8 Flash
- DeepSeek V4 Pro public-lane score: 59.7 (Supported · #46/158)
- Gemini 3.8 Flash public-lane score: 71.5 (Supported · #16/158)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 87.5% | Coming soon | Coming soon |
| Chinese-SimpleQA | 84.4% | Coming soon | Coming soon |
| GPQA | 90.1% | Coming soon | Coming soon |
| GPQA-D | 90.1% | Coming soon | Coming soon |
| HLE | 42.7% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 92.4% | 94.4% | Gemini 3.8 Flash |
| MMLU-Pro (Vals) | 87.0% | 90.2% | Gemini 3.8 Flash |
| HLE-Verified | Coming soon | 54.9% | Coming soon |
| LABBench2 | Coming soon | 86.2% | Coming soon |
| BioMysteryBench (human-solvable) | Coming soon | 88.8% | Coming soon |
| BioMysteryBench (human-difficult) | Coming soon | 56.5% | Coming soon |

### Multilingual

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 57.3 (Estimated · #31/88)
- Gemini 3.8 Flash public-lane score: 66.2 (Estimated · #13/88)

### Instruction Following

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 56.6 (Supported · #47/143)
- Gemini 3.8 Flash public-lane score: 65.6 (Estimated · #21/143)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 5.5% | Coming soon |

### Mathematics

- Winner: Gemini 3.8 Flash
- DeepSeek V4 Pro public-lane score: 59.4 (Supported · #34/125)
- Gemini 3.8 Flash public-lane score: 64.3 (Supported · #24/125)

| Benchmark | DeepSeek V4 Pro | Gemini 3.8 Flash | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 95.2% | Coming soon | Coming soon |
| IMOAnswerBench | 89.8% | Coming soon | Coming soon |
| Apex | 38.3% | Coming soon | Coming soon |
| Apex Shortlist | 90.2% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 64.561% | 68.421% | Gemini 3.8 Flash |
| FrontierMath v2 (Tier 4) | 26.829% | 21.951% | DeepSeek V4 Pro |

## FAQ

### Which is better overall, DeepSeek V4 Pro or Gemini 3.8 Flash?

Gemini 3.8 Flash is ahead overall on BenchLM right now.

### Where is the biggest gap between DeepSeek V4 Pro and Gemini 3.8 Flash?

The widest category gap is in knowledge, where the averages are 59.7 for DeepSeek V4 Pro and 71.5 for Gemini 3.8 Flash.

### How many benchmarks does DeepSeek V4 Pro cover on BenchLM?

DeepSeek V4 Pro currently has 46 sourced benchmark scores on BenchLM.

### How many benchmarks does Gemini 3.8 Flash cover on BenchLM?

Gemini 3.8 Flash currently has 37 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Pro vs Gemini 3.8 Flash Cyber](/compare/deepseek-v4-pro-vs-gemini-3-8-flash-cyber)
- [Gemini 3.8 Flash vs Gemini 3.8 Flash Cyber](/compare/gemini-3-8-flash-vs-gemini-3-8-flash-cyber)
- [DeepSeek V4 Pro vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-deepseek-v4-pro)
- [Gemini 3.8 Flash vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-gemini-3-8-flash)

## Explore More

- [DeepSeek V4 Pro profile](/models/deepseek-v4-pro)
- [Gemini 3.8 Flash profile](/models/gemini-3-8-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
