# LFM3-VL-2B vs MiMo-V2.5

> Side-by-side benchmark comparison for LFM3-VL-2B and MiMo-V2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/lfm3-vl-2b-vs-mimo-v2-5
- Last updated: October 27, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: LFM3-VL-2B and MiMo-V2.5 share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- MiMo-V2.5 has the lower published output-token price.
- MiMo-V2.5 has the larger published context window at 1M.

## Model Snapshot

| Property | LFM3-VL-2B | MiMo-V2.5 |
|----------|----------|----------|
| Creator | LiquidAI | Xiaomi |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 1M |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 20 | 15 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- LFM3-VL-2B public-lane score: Coming soon
- MiMo-V2.5 public-lane score: 33.9 (Estimated · #91/134)

| Benchmark | LFM3-VL-2B | MiMo-V2.5 | Winner |
|-----------|-----------|-----------|--------|
| Claw-Eval | Coming soon | 62.3% | Coming soon |
| MM-ClawBench | Coming soon | 23.8% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 65.8% | Coming soon |
| Gert Labs | Coming soon | 46.89% | Coming soon |
| ResearchClawBench | Coming soon | 16.9% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 60.7% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- LFM3-VL-2B public-lane score: Coming soon
- MiMo-V2.5 public-lane score: 35.2 (Supported · #81/155)

| Benchmark | LFM3-VL-2B | MiMo-V2.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | Coming soon | 56.1% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 65.8% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 81.5% | Coming soon |
| SWE-bench (Vals) | Coming soon | 71.0% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- LFM3-VL-2B public-lane score: 19.6 (Unranked · 19 rankable rows)
- MiMo-V2.5 public-lane score: 71.9 (#34/58)

| Benchmark | LFM3-VL-2B | MiMo-V2.5 | 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% | Coming soon | Coming soon |
| MMMU-Pro | 45.7% | 77.9% | MiMo-V2.5 |
| OCRBench V2 | 63.5% | Coming soon | Coming soon |
| RefCOCO (avg) | 90.5% | Coming soon | Coming soon |
| V* | 86.4% | Coming soon | Coming soon |
| CharXiv w/o tools | 70.2% | Coming soon | Coming soon |
| MathVision | 51.6% | Coming soon | Coming soon |
| 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% | Coming soon | Coming soon |
| Video-MME (w/o subtitle) | 62.8% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 69.0% | 87.7% | MiMo-V2.5 |
| VideoMMMU | 49.6% | Coming soon | Coming soon |
| CharXiv | Coming soon | 81% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- LFM3-VL-2B public-lane score: Coming soon
- MiMo-V2.5 public-lane score: Coming soon

| Benchmark | LFM3-VL-2B | MiMo-V2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | Coming soon | 81.6% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 82.9% | Coming soon |

## FAQ

### Is there enough evidence to pick between LFM3-VL-2B and MiMo-V2.5?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [LFM3-VL-2B vs MiMo-V2.5-Pro](/compare/lfm3-vl-2b-vs-mimo-v2-5-pro)
- [MiMo-V2.5 vs MiMo-V2.5-Pro](/compare/mimo-v2-5-vs-mimo-v2-5-pro)
- [LFM3-VL-2B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-lfm3-vl-2b)
- [MiMo-V2.5 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-mimo-v2-5)

## Explore More

- [LFM3-VL-2B profile](/models/lfm3-vl-2b)
- [MiMo-V2.5 profile](/models/mimo-v2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)