# LFM2.5-2.6B Benchmark Scores & Performance

> LFM2.5-2.6B by LiquidAI scores 39.9/100 overall, ranking #175 out of 491 AI models.

Canonical page: https://benchlm.ai/models/lfm2-5-2-6b

Last updated: September 18, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LiquidAI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Official model card | [LiquidAI LFM2.5-2.6B model card](https://huggingface.co/LiquidAI/LFM2.5-2.6B) |
| Overall Score | 39.9/100 |
| Overall Rank | #175 of 491 |

## Family & Coverage

- Family: LFM2.5-2.6B
- Variant: reasoning
- Benchmarks covered: 19 of 446
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [BFCL v4](/benchmarks/bfcl-v4) | 56.9% |
| [τ³-bench results](/benchmarks/tau3-bench) | 5.7% |
| [Claw-Eval](/benchmarks/claw-eval) | 62.9% |
| [PinchBench](/benchmarks/pinchbench) | 68.2% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 0.0% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 202 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 59.4% |
| [AA-SciCode](/benchmarks/aascicode) | 14.4% |
| [AA Coding Index](/benchmarks/aacodingindex) | 7.7% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 5.7% |
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -29.5% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 8.4% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 55.8% |
| [AA-HLE](/benchmarks/aahle) | 6.2% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 4.4% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 16.0% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFBench](/benchmarks/ifbench) | 59.2% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME 2025](/benchmarks/aime2025) | 51.9% |

## Other LiquidAI Models

- [LFM2.5-8B-A1B](/models/lfm2-5-8b-a1b) - Score: 39.28
- [LFM2-24B-A2B](/models/lfm2-24b-a2b) - Score: 18.48
- [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) - Score: 16.65
- [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) - Score: 15.97
- [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
- [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
- [LFM2.5-350M](/models/lfm2-5-350m) - Score: not computed