# DeepSeek V4 Pro 0813 vs LFM3-1.7B

> Side-by-side benchmark comparison for DeepSeek V4 Pro 0813 and LFM3-1.7B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-0813-vs-lfm3-1-7b
- Last updated: October 27, 2026

- Shared sourced benchmarks: 10
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

DeepSeek V4 Pro 0813 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- DeepSeek V4 Pro 0813 has the higher overall point estimate 63.36 to 22.99. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 53.4 for DeepSeek V4 Pro 0813 and 14.4 for LFM3-1.7B.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 87.9% and 12.9%.
- LFM3-1.7B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- DeepSeek V4 Pro 0813 also has the larger context window at 1M.

## Model Snapshot

| Property | DeepSeek V4 Pro 0813 | LFM3-1.7B |
|----------|----------|----------|
| Creator | DeepSeek | LiquidAI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 256K |
| Overall Score | 63.36 | 22.99 |
| Benchmarks Covered | 41 | 24 |
| Pricing (input/output) | $1.32 / $3.96 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- DeepSeek V4 Pro 0813 public-lane score: 53.4 (Supported · #47/134)
- LFM3-1.7B public-lane score: 14.4 (Estimated · #123/134)

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | 12.9% | DeepSeek V4 Pro 0813 |
| BrowseComp | 83.4% | Coming soon | Coming soon |
| HLE w/ tools | 60.0% | 13.9% | DeepSeek V4 Pro 0813 |
| MCP Atlas | 73.6% | 32.6% | DeepSeek V4 Pro 0813 |
| 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% | 41.3% | LFM3-1.7B |
| Terminal-Bench 2.1 (Vals) | 54.7% | Coming soon | Coming soon |
| BFCL v4 | Coming soon | 71.4% | Coming soon |
| τ³-bench results | Coming soon | 68.0% | Coming soon |
| WebArena-Verified | Coming soon | 38.4% | Coming soon |
| ToolSandbox | Coming soon | 80.36% | Coming soon |
| Claw-Eval | Coming soon | 68.6% | Coming soon |
| LiveClaw | Coming soon | 45.60% | Coming soon |

### Coding

- Winner: Directional only
- DeepSeek V4 Pro 0813 public-lane score: 47.5 (Supported · #52/155)
- LFM3-1.7B public-lane score: 13 (Estimated · #142/155)

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 93.5% | Coming soon | Coming soon |
| Codeforces | 3206.0 | Coming soon | Coming soon |
| SWE-bench Verified | 80.6% | 43.4% | DeepSeek V4 Pro 0813 |
| SWE-bench Pro | 55.4% | Coming soon | Coming soon |
| SWE Multilingual | 76.2% | 23% | DeepSeek V4 Pro 0813 |
| 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% | 12.9% | DeepSeek V4 Pro 0813 |
| NL2Repo | 61.5% | Coming soon | Coming soon |
| DeepSWE | 62.7% | Coming soon | Coming soon |
| DSBench-FullStack | 71.1% | Coming soon | Coming soon |
| DSBench-Hard | 67.2% | Coming soon | Coming soon |
| OpenHarmony Bench | 59.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 96.4% | Coming soon | Coming soon |
| SciCode | Coming soon | 28.5% | Coming soon |
| LiveCodeBench v6 | Coming soon | 73.5% | Coming soon |
| LiveCodeBench Pro | Coming soon | 31.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek V4 Pro 0813 public-lane score: 60.7 (Unranked · 4 rankable rows)
- LFM3-1.7B public-lane score: 61.3 (Unranked · 1 rankable row)

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 83.5% | Coming soon | Coming soon |
| CorpusQA 1M | 62.0% | Coming soon | Coming soon |
| ARC-AGI-1 | 90.00% | Coming soon | Coming soon |
| ARC-AGI-2 | 61.3% | Coming soon | Coming soon |
| RULER (128K) | Coming soon | 65.56% | Coming soon |

### Knowledge

- Winner: Directional only
- DeepSeek V4 Pro 0813 public-lane score: 63.2 (Estimated · #43/189)
- LFM3-1.7B public-lane score: 25.5 (Estimated · #175/189)

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 87.5% | Coming soon | Coming soon |
| Chinese-SimpleQA | 84.4% | Coming soon | Coming soon |
| GPQA | 90.1% | 63.4% | DeepSeek V4 Pro 0813 |
| GPQA-D | 90.1% | 63.4% | DeepSeek V4 Pro 0813 |
| HLE | 42.7% | 7.2% | DeepSeek V4 Pro 0813 |
| GPQA Diamond (Vals) | 92.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.0% | Coming soon | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4 Pro 0813 public-lane score: Coming soon
- LFM3-1.7B public-lane score: 71.7 (#76/156)

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 96.7% | Coming soon |
| IFBench | Coming soon | 73.0% | Coming soon |
| Multi-IF | Coming soon | 89.10% | Coming soon |
| IFStruct | Coming soon | 93.72% | Coming soon |

### Mathematics

- Winner: Not comparable
- DeepSeek V4 Pro 0813 public-lane score: 87.4 (Unranked · 4 rankable rows)
- LFM3-1.7B public-lane score: Coming soon

| Benchmark | DeepSeek V4 Pro 0813 | LFM3-1.7B | 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 |

## FAQ

### Which is better overall, DeepSeek V4 Pro 0813 or LFM3-1.7B?

DeepSeek V4 Pro 0813 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between DeepSeek V4 Pro 0813 and LFM3-1.7B?

The widest category gap is in agentic, where the averages are 53.4 for DeepSeek V4 Pro 0813 and 14.4 for LFM3-1.7B.

### How many benchmarks does DeepSeek V4 Pro 0813 cover on BenchLM?

DeepSeek V4 Pro 0813 currently has 41 sourced benchmark scores on BenchLM.

### How many benchmarks does LFM3-1.7B cover on BenchLM?

LFM3-1.7B currently has 24 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Pro 0813 vs LFM3-1.7B-Base](/compare/deepseek-v4-pro-0813-vs-lfm3-1-7b-base)
- [LFM3-1.7B vs LFM3-1.7B-Base](/compare/lfm3-1-7b-vs-lfm3-1-7b-base)
- [DeepSeek V4 Pro 0813 vs LFM3-Audio-2B](/compare/deepseek-v4-pro-0813-vs-lfm3-audio-2b)
- [LFM3-1.7B vs LFM3-Audio-2B](/compare/lfm3-1-7b-vs-lfm3-audio-2b)

## Explore More

- [DeepSeek V4 Pro 0813 profile](/models/deepseek-v4-pro-0813)
- [LFM3-1.7B profile](/models/lfm3-1-7b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)