# Inkling 2 Mini vs LFM3-1.7B

> Side-by-side benchmark comparison for Inkling 2 Mini and LFM3-1.7B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/inkling-2-mini-vs-lfm3-1-7b
- Last updated: November 21, 2026

- Shared sourced benchmarks: 7
- HTML indexing: indexable
- Ranking lane: BenchAlign v6.0

## Quick Verdict

Inkling 2 Mini leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Inkling 2 Mini has the higher overall point estimate 55.9 to 31. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 53.9 for Inkling 2 Mini and 24.8 for LFM3-1.7B.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 71.6% and 12.9%.
- LFM3-1.7B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Inkling 2 Mini also has the larger context window at 1M.

## Model Snapshot

| Property | Inkling 2 Mini | LFM3-1.7B |
|----------|----------|----------|
| Creator | Thinking Machines Lab | LiquidAI |
| Type | Open Weight | Open Weight |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 256K |
| Overall Score | 55.9 | 31 |
| Benchmarks Covered | 33 | 24 |
| Pricing (input/output) | $0.15 / $0.50 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Inkling 2 Mini public-lane score: 59.1 (Estimated · #61/179)
- LFM3-1.7B public-lane score: 36.3 (Estimated · #147/179)

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 5.60% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 71.6% | 12.9% | Inkling 2 Mini |
| Terminal-Bench-Science 0.1 | 1.4% | Coming soon | Coming soon |
| BrowseComp | 79% | Coming soon | Coming soon |
| DeepSearchQA | 85.3% | Coming soon | Coming soon |
| MCP Atlas | 82.7% | 32.6% | Inkling 2 Mini |
| JobBench | 49.6% | Coming soon | Coming soon |
| EnterpriseOps-Gym | 42.00% | Coming soon | Coming soon |
| AutomationBench | Coming soon | 41.3% | 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 |
| HLE w/ tools | Coming soon | 13.9% | Coming soon |
| LiveClaw | Coming soon | 45.60% | Coming soon |

### Coding

- Winner: Directional only
- Inkling 2 Mini public-lane score: 53.9 (Estimated · #67/179)
- LFM3-1.7B public-lane score: 24.8 (Estimated · #171/179)

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| FrontierCode 2.0 | 15.1% | Coming soon | Coming soon |
| DeepSWE | 48.2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 71.6% | 12.9% | Inkling 2 Mini |
| SWE Multilingual | 73.7% | 23% | Inkling 2 Mini |
| SWE-bench Verified | 79.2% | 43.4% | Inkling 2 Mini |
| 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
- Inkling 2 Mini public-lane score: 57.8 (Estimated · #58/161)
- LFM3-1.7B public-lane score: Coming soon

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 66.9% | Coming soon | Coming soon |
| MRCR v2 256K-512K | 46.4% | Coming soon | Coming soon |
| RULER (128K) | Coming soon | 65.56% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Inkling 2 Mini public-lane score: 55.5 (Estimated · #62/119)
- LFM3-1.7B public-lane score: Coming soon

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| PerceptionBench | 57.5% | Coming soon | Coming soon |
| MMMU-Pro | 74.9% | Coming soon | Coming soon |
| OmniDocBench 1.6 | 92.8% | Coming soon | Coming soon |
| BabyVision | 53.4% | Coming soon | Coming soon |
| BabyVision w/ Python | 88.8% | Coming soon | Coming soon |
| ScreenSpot Pro | 76.5% | Coming soon | Coming soon |
| CharXiv | 88.3% | Coming soon | Coming soon |
| CharXiv w/o tools | 80.6% | Coming soon | Coming soon |
| Chartography (no tools) | 22.1% | Coming soon | Coming soon |
| Chartography (tools) | 72.5% | Coming soon | Coming soon |
| ZeroBench | 17.0% | Coming soon | Coming soon |
| ZeroBench w/ Python | 34.0% | Coming soon | Coming soon |
| MathVision | 89.0% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Inkling 2 Mini public-lane score: 51.9 (Estimated · #79/158)
- LFM3-1.7B public-lane score: 29 (Estimated · #149/158)

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 86.6% | 63.4% | Inkling 2 Mini |
| GPQA-D | 86.6% | 63.4% | Inkling 2 Mini |
| HLE w/o tools | 30.7% | Coming soon | Coming soon |
| HLE | Coming soon | 7.2% | Coming soon |

### Multilingual

- Winner: Directional only
- Inkling 2 Mini public-lane score: 54.7 (Estimated · #39/87)
- LFM3-1.7B public-lane score: 25.7 (Estimated · #86/87)

### Instruction Following

- Winner: Not comparable
- Inkling 2 Mini public-lane score: Coming soon
- LFM3-1.7B public-lane score: 32.9 (Estimated · #132/143)

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| MultiChallenge (provider reports) | 50.00% | Coming soon | Coming soon |
| 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
- Inkling 2 Mini public-lane score: Coming soon
- LFM3-1.7B public-lane score: Coming soon

| Benchmark | Inkling 2 Mini | LFM3-1.7B | Winner |
|-----------|-----------|-----------|--------|
| Apex | 34.4% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Inkling 2 Mini or LFM3-1.7B?

Inkling 2 Mini has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Inkling 2 Mini and LFM3-1.7B?

The widest category gap is in coding, where the averages are 53.9 for Inkling 2 Mini and 24.8 for LFM3-1.7B.

### How many benchmarks does Inkling 2 Mini cover on BenchLM?

Inkling 2 Mini currently has 33 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

- [Inkling 2 Mini vs Inkling 2 Small](/compare/inkling-2-mini-vs-inkling-2-small)
- [LFM3-1.7B vs Inkling 2 Small](/compare/inkling-2-small-vs-lfm3-1-7b)
- [Inkling 2 Mini vs Inkling](/compare/inkling-vs-inkling-2-mini)
- [LFM3-1.7B vs Inkling](/compare/inkling-vs-lfm3-1-7b)

## Explore More

- [Inkling 2 Mini profile](/models/inkling-2-mini)
- [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)
