# LFM3-1.7B Benchmark Scores & Performance

> LFM3-1.7B by LiquidAI scores 22.99/100 overall, ranking #215 out of 1000 AI models.

Canonical page: https://benchlm.ai/models/lfm3-1-7b

Last updated: October 27, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LiquidAI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Official model card | [Liquid AI LFM3-1.7B model card](https://huggingface.co/LiquidAI/LFM3-1.7B/blob/40ebe0aa6662c9d40389c2f5d565b6a2c6aebacd/README.md) |
| Overall Score | 22.99/100 |
| Overall Rank | #215 of 1000 |

## Family & Coverage

- Family: LFM3
- Variant: reasoning
- Benchmarks covered: 28 of 716
- Sibling models: [LFM3-1.7B-Base](/models/lfm3-1-7b-base), [LFM3-Audio-2B](/models/lfm3-audio-2b), [LFM3-Omni-2B](/models/lfm3-omni-2b)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AutomationBench](/benchmarks/automationbench) | 41.3% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [BFCL v4](/benchmarks/bfcl-v4) | 71.4% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [τ³-bench results](/benchmarks/tau3-bench) | 68.0% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [WebArena-Verified](/benchmarks/webarena-verified) | 38.4% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [MCP Atlas](/benchmarks/mcpatlas) | 32.6% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [ToolSandbox](/benchmarks/toolsandbox) | 80.36% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [Claw-Eval](/benchmarks/claw-eval) | 68.6% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [HLE w/ tools](/benchmarks/hlewithtools) | 13.9% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 12.9% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [LiveClaw](/benchmarks/liveclaw) | 45.60% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [EnterpriseOps-Gym](/benchmarks/enterpriseopsgym) | 28.20% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SciCode](/benchmarks/scicode) | 28.5% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 43.4% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 23% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 12.9% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 73.5% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [LiveCodeBench Pro](/benchmarks/livecodebench-pro) | 31.7% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 52.8% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [RULER (128K)](/benchmarks/ruler128k) | 65.56% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 63.4% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [GPQA-D](/benchmarks/gpqa-diamond) | 63.4% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [HLE](/benchmarks/hle) | 7.2% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 0.5% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 7.1% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 96.7% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [IFBench](/benchmarks/ifbench) | 73.0% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [Multi-IF](/benchmarks/multiif) | 89.10% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |
| [IFStruct](/benchmarks/ifstruct) | 93.72% | [Liquid AI: LFM3 launch post and LFM3-1.7B model card](https://www.liquid.ai/blog/lfm3) |

## Other LiquidAI Models

- [LFM2.5-24B-A2B](/models/lfm2-5-24b-a2b) - Score: 36.99
- [LFM2.5-2.6B](/models/lfm2-5-2-6b) - Score: 31.4
- [LFM2.5-8B-A1B](/models/lfm2-5-8b-a1b) - Score: 30.31
- [LFM2-24B-A2B](/models/lfm2-24b-a2b) - Score: 20.74
- [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) - Score: 19.5
- [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) - Score: 19.25
- [LFM2.5-350M](/models/lfm2-5-350m) - Score: not computed
- [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) - Score: not computed
- [LFM3-VL-2B](/models/lfm3-vl-2b) - Score: not computed
- [LFM2.5-230M](/models/lfm2-5-230m) - Score: not computed
- [LFM2.5-VL-3B](/models/lfm2-5-vl-3b) - Score: not computed
- [LFM2.5-VL-1.6B-Extract](/models/lfm2-5-vl-1-6b-extract) - Score: not computed
- [LFM2.5-VL-450M-Extract](/models/lfm2-5-vl-450m-extract) - Score: not computed
- [d1-2B](/models/d1-2b) - Score: not computed
- [d1-Omni-2B](/models/d1-omni-2b) - Score: not computed
- [LFM3-1.7B-Base](/models/lfm3-1-7b-base) - Score: not computed
- [LFM3-Audio-2B](/models/lfm3-audio-2b) - Score: not computed
- [LFM3-Omni-2B](/models/lfm3-omni-2b) - Score: not computed
- [d1-3B](/models/d1-3b) - Score: not computed
- [d1-omni-600M](/models/d1-omni-600m) - Score: not computed
- [LFM2.5-ColBERT-350M](/models/lfm2-5-colbert-350m) - Score: not computed
- [LFM2.5-Embedding-350M](/models/lfm2-5-embedding-350m) - Score: not computed
- [LFM2.5-1.2B-JP-202606](/models/lfm2-5-1-2b-jp-202606) - Score: not computed