# LFM2.5-8B-A1B Benchmark Scores & Performance

> LFM2.5-8B-A1B by LiquidAI scores 30.19/100 overall, ranking #177 out of 935 AI models.

Canonical page: https://benchlm.ai/models/lfm2-5-8b-a1b

Last updated: October 14, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LiquidAI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | 30.19/100 |
| Overall Rank | #177 of 935 |

## Family & Coverage

- Family: LFM2.5-8B-A1B
- Variant: reasoning
- Benchmarks covered: 16 of 629
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [BFCL v4](/benchmarks/bfcl-v4) | 49.7% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [τ²-bench results](/benchmarks/tau2-bench) | 88.1% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 0.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |
| [CritPt](/benchmarks/critpt) | 0.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 51.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |
| [AA-HLE](/benchmarks/aahle) | 6.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -33.3% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 9.4% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 46.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 7.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 91.8% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [IFBench](/benchmarks/ifbench) | 56.5% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [AA-IFBench](/benchmarks/ifbench) | 55.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/lfm2-5-8b-a1b) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MATH-500](/benchmarks/math-500) | 88.8% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [AIME 2025](/benchmarks/aime2025) | 42.5% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |
| [AIME26](/benchmarks/aime2026) | 50.0% | [Liquid AI: LFM2.5-8B-A1B launch post](https://www.liquid.ai/blog/lfm2-5-8b-a1b) |

## Other LiquidAI Models

- [LFM2.5-24B-A2B](/models/lfm2-5-24b-a2b) - Score: 38.08
- [LFM2.5-2.6B](/models/lfm2-5-2-6b) - Score: 31.27
- [LFM2-24B-A2B](/models/lfm2-24b-a2b) - Score: 20.74
- [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) - Score: 19.51
- [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) - Score: 19.26
- [LFM2.5-350M](/models/lfm2-5-350m) - Score: not computed
- [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) - 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
- [d1-3B](/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