# LFM3-VL-2B vs Qwen3.5-35B-A3B

> Side-by-side benchmark comparison for LFM3-VL-2B and Qwen3.5-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/lfm3-vl-2b-vs-qwen3-5-35b-a3b
- Last updated: October 27, 2026

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

## Quick Verdict

Pick Qwen3.5-35B-A3B if you want the stronger benchmark profile. LFM3-VL-2B only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Qwen3.5-35B-A3B leads overall 46.02 to 39.
- The clearest category separation is in multimodal & grounded, where the averages are 19.6 for LFM3-VL-2B and 64.8 for Qwen3.5-35B-A3B.
- The biggest single benchmark swing is MathVision in Multimodal & Grounded, with scores of 51.6% and 83.9%.
- Qwen3.5-35B-A3B also has the larger context window at 262K.

## Model Snapshot

| Property | LFM3-VL-2B | Qwen3.5-35B-A3B |
|----------|----------|----------|
| Creator | LiquidAI | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 262K |
| Overall Score | null | 46.02 |
| Benchmarks Covered | 20 | 21 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 34.3 (Estimated · #89/134)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | Coming soon | 40.5% | Coming soon |
| BrowseComp | Coming soon | 61% | Coming soon |
| OSWorld-Verified | Coming soon | 54.5% | Coming soon |
| Gert Labs | Coming soon | 28.96% | Coming soon |

### Coding

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 26.3 (Estimated · #109/155)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | Coming soon | 69.2% | Coming soon |
| LiveCodeBench v6 | Coming soon | 74.6% | Coming soon |
| SWE-Rebench | Coming soon | 53.7% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 40.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 64.4 (Unranked · 3 rankable rows)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 59% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- LFM3-VL-2B public-lane score: 19.6 (Unranked · 19 rankable rows)
- Qwen3.5-35B-A3B public-lane score: 64.8 (#46/58)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| RealWorldQA | 79.3% | Coming soon | Coming soon |
| SimpleVQA | 36.3% | Coming soon | Coming soon |
| CountBench | 93.0% | Coming soon | Coming soon |
| MMMU | 55.7% | 81.4% | Qwen3.5-35B-A3B |
| MMMU-Pro | 45.7% | 75.1% | Qwen3.5-35B-A3B |
| OCRBench V2 | 63.5% | Coming soon | Coming soon |
| RefCOCO (avg) | 90.5% | Coming soon | Coming soon |
| V* | 86.4% | 92.7% | Qwen3.5-35B-A3B |
| CharXiv w/o tools | 70.2% | Coming soon | Coming soon |
| MathVision | 51.6% | 83.9% | Qwen3.5-35B-A3B |
| DynaMath | 79.2% | Coming soon | Coming soon |
| We-Math | 68.6% | Coming soon | Coming soon |
| ERQA | 48.2% | Coming soon | Coming soon |
| ScreenSpot Pro | 55.5% | Coming soon | Coming soon |
| LVBench | 41.2% | Coming soon | Coming soon |
| MLVU (M-Avg) | 71.3% | Coming soon | Coming soon |
| MMVU | 52.9% | 72.3% | Qwen3.5-35B-A3B |
| Video-MME (w/o subtitle) | 62.8% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 69.0% | Coming soon | Coming soon |
| VideoMMMU | 49.6% | Coming soon | Coming soon |
| ExtractBench (LlamaIndex) | Coming soon | 88.00% | Coming soon |
| CharXiv | Coming soon | 77.5% | Coming soon |

### Knowledge

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 43.2 (Supported · #110/189)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | Coming soon | 85.3% | Coming soon |
| SuperGPQA | Coming soon | 63.4% | Coming soon |
| GPQA | Coming soon | 84.2% | Coming soon |

### Multilingual

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 83.8 (#11/17)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 81% | Coming soon |

### Instruction Following

- Winner: Not comparable
- LFM3-VL-2B public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 88.8 (#36/156)

| Benchmark | LFM3-VL-2B | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 91.9% | Coming soon |

## FAQ

### Which is better overall, LFM3-VL-2B or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B is ahead overall on BenchLM right now.

### Where is the biggest gap between LFM3-VL-2B and Qwen3.5-35B-A3B?

The widest category gap is in multimodal & grounded, where the averages are 19.6 for LFM3-VL-2B and 64.8 for Qwen3.5-35B-A3B.

### How many benchmarks does LFM3-VL-2B cover on BenchLM?

LFM3-VL-2B currently has 20 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3.5-35B-A3B cover on BenchLM?

Qwen3.5-35B-A3B currently has 21 sourced benchmark scores on BenchLM.

## Related Comparisons

- [LFM3-VL-2B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-lfm3-vl-2b)
- [Qwen3.5-35B-A3B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-5-35b-a3b)
- [LFM3-VL-2B vs GPT-6 Astra](/compare/gpt-6-astra-vs-lfm3-vl-2b)
- [Qwen3.5-35B-A3B vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-5-35b-a3b)

## Explore More

- [LFM3-VL-2B profile](/models/lfm3-vl-2b)
- [Qwen3.5-35B-A3B profile](/models/qwen3-5-35b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)