# DeepSeek V4.1 Flash 1017 vs Ripple-65B Preview

> Side-by-side benchmark comparison for DeepSeek V4.1 Flash 1017 and Ripple-65B Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-1-flash-vs-ripple-65b-preview
- Last updated: November 4, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick DeepSeek V4.1 Flash 1017 if you want the stronger benchmark profile. Ripple-65B Preview only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- DeepSeek V4.1 Flash 1017 leads overall 65.22 to 0.
- The biggest single benchmark swing is DeepSWE in Coding, with scores of 77.0% and 44.3%.
- Ripple-65B Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview |
|----------|----------|----------|
| Creator | DeepSeek | Ricursive Intelligence |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 65.22 | null |
| Benchmarks Covered | 35 | 17 |
| Pricing (input/output) | $0.30 / $1.20 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 62.2 (Supported · #21/135)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 90.6% | 80.5% | DeepSeek V4.1 Flash 1017 |
| terminalBench3 | 30% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | 42.30% | Coming soon | Coming soon |
| CyberGym | 88.1% | Coming soon | Coming soon |
| ExploitGym | 15.3% | Coming soon | Coming soon |
| HLE w/ tools | 63.9% | Coming soon | Coming soon |
| AutomationBench | 60.5% | 36.4% | DeepSeek V4.1 Flash 1017 |
| Agents' Last Exam | 35.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 74.5% | Coming soon | Coming soon |
| CWE-bench v1 | 55.0% | Coming soon | Coming soon |
| MazeBench | 1% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 31.3% | Coming soon |
| MCP Atlas | Coming soon | 71.7% | Coming soon |

### Coding

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 62.9 (Supported · #14/156)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| ScarfBench | 69.0% | Coming soon | Coming soon |
| Codeforces | 3471.0 | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 90.6% | 80.5% | DeepSeek V4.1 Flash 1017 |
| terminalBench3 | 30% | Coming soon | Coming soon |
| DeepSWE | 77.0% | 44.3% | DeepSeek V4.1 Flash 1017 |
| ProgramBench | 29.1% | Coming soon | Coming soon |
| NL2Repo | 68.2% | Coming soon | Coming soon |
| OpenHarmony Bench | 60.3% | Coming soon | Coming soon |
| Bug Hunt Bench | 39.1 fixes | Coming soon | Coming soon |
| FrontierCode 2.0 | 19.3% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 76.5% | Coming soon |
| SWE-bench Pro | Coming soon | 61.4% | Coming soon |
| SciCode | Coming soon | 39.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 82.5 (Unranked · 4 rankable rows)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| STEMBench | 2.54 | Coming soon | Coming soon |
| JevBench 1.4 | 4.77 | Coming soon | Coming soon |
| JevBench 1.5 | 6.65 | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 78.2 (Unranked · 1 rankable row)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| ExtractBench (LlamaIndex) | 87.11% | Coming soon | Coming soon |
| ParseBench | 64.56% | Coming soon | Coming soon |
| Chartography (tools) | 83.0% | Coming soon | Coming soon |
| BabyVision w/ Python | 92.5% | Coming soon | Coming soon |
| ZeroBench w/ Python | 51.0% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 64.2 (Supported · #38/179)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 90.9% | Coming soon | Coming soon |
| GPQA-D | 90.9% | 85.2% | DeepSeek V4.1 Flash 1017 |
| HLE | 42.6% | Coming soon | Coming soon |
| MMLU | Coming soon | 89.6% | Coming soon |
| MMLU-Pro | Coming soon | 84.2% | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: Coming soon
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 79.2% | Coming soon |

### Mathematics

- Winner: Not comparable
- DeepSeek V4.1 Flash 1017 public-lane score: 70.1 (Unranked · 3 rankable rows)
- Ripple-65B Preview public-lane score: Coming soon

| Benchmark | DeepSeek V4.1 Flash 1017 | Ripple-65B Preview | Winner |
|-----------|-----------|-----------|--------|
| Apex | 65.6% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 67.368% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 26.829% | Coming soon | Coming soon |
| AIME 2024 | Coming soon | 97.1% | Coming soon |
| AIME 2025 | Coming soon | 98.3% | Coming soon |
| AIME26 | Coming soon | 95.0% | Coming soon |
| HMMT Feb 2026 | Coming soon | 90.5% | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4.1 Flash 1017 or Ripple-65B Preview?

DeepSeek V4.1 Flash 1017 is ahead overall on BenchLM right now.

### How many benchmarks does DeepSeek V4.1 Flash 1017 cover on BenchLM?

DeepSeek V4.1 Flash 1017 currently has 35 sourced benchmark scores on BenchLM.

### How many benchmarks does Ripple-65B Preview cover on BenchLM?

Ripple-65B Preview currently has 17 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4.1 Flash 1017 vs Gemini 4 Carbon](/compare/deepseek-v4-1-flash-vs-gemini-4-carbon)
- [Ripple-65B Preview vs Gemini 4 Carbon](/compare/gemini-4-carbon-vs-ripple-65b-preview)
- [DeepSeek V4.1 Flash 1017 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-deepseek-v4-1-flash)
- [Ripple-65B Preview vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-ripple-65b-preview)

## Explore More

- [DeepSeek V4.1 Flash 1017 profile](/models/deepseek-v4-1-flash)
- [Ripple-65B Preview profile](/models/ripple-65b-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)