# LFM2.5-24B-A2B vs LFM2.5-8B-A1B

> Side-by-side benchmark comparison for LFM2.5-24B-A2B and LFM2.5-8B-A1B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/lfm2-5-24b-a2b-vs-lfm2-5-8b-a1b
- Last updated: October 13, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

LFM2.5-24B-A2B leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- LFM2.5-24B-A2B has the higher overall point estimate 37.8 to 30.02. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 75.6 for LFM2.5-24B-A2B and 36.5 for LFM2.5-8B-A1B.
- The biggest single benchmark swing is IFBench in Instruction Following, with scores of 74.7% and 56.5%.
- LFM2.5-8B-A1B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- LFM2.5-24B-A2B also has the larger context window at 131K.

## Model Snapshot

| Property | LFM2.5-24B-A2B | LFM2.5-8B-A1B |
|----------|----------|----------|
| Creator | LiquidAI | LiquidAI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 131K | 128K |
| Overall Score | 37.8 | 30.02 |
| Benchmarks Covered | 13 | 7 |
| Pricing (input/output) | $0.10 / $1.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- LFM2.5-24B-A2B public-lane score: 30.2 (Estimated · #88/124)
- LFM2.5-8B-A1B public-lane score: Coming soon

| Benchmark | LFM2.5-24B-A2B | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| AutomationBench | 27.7% | Coming soon | Coming soon |
| BFCL v4 | 65.0% | 49.7% | LFM2.5-24B-A2B |
| τ³-bench results | 8.0% | Coming soon | Coming soon |
| PinchBench | 83.2% | Coming soon | Coming soon |
| WebArena-Verified | 26.8% | Coming soon | Coming soon |
| τ²-bench results | Coming soon | 88.1% | Coming soon |

### Coding

- Winner: Not comparable
- LFM2.5-24B-A2B public-lane score: 28.5 (Estimated · #98/149)
- LFM2.5-8B-A1B public-lane score: Coming soon

| Benchmark | LFM2.5-24B-A2B | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| SciCode | 32.7% | Coming soon | Coming soon |
| SWE-bench Verified | 51% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- LFM2.5-24B-A2B public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 25.9 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Directional only
- LFM2.5-24B-A2B public-lane score: 40.8 (Estimated · #112/181)
- LFM2.5-8B-A1B public-lane score: 26.6 (Supported · #166/181)

| Benchmark | LFM2.5-24B-A2B | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 74.4% | Coming soon | Coming soon |
| GPQA-D | 74.4% | Coming soon | Coming soon |
| HLE | 7.4% | Coming soon | Coming soon |

### Instruction Following

- Winner: LFM2.5-24B-A2B
- LFM2.5-24B-A2B public-lane score: 75.6 (#61/128)
- LFM2.5-8B-A1B public-lane score: 36.5 (#110/128)

| Benchmark | LFM2.5-24B-A2B | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 96.8% | 91.8% | LFM2.5-24B-A2B |
| IFBench | 74.7% | 56.5% | LFM2.5-24B-A2B |

### Mathematics

- Winner: Not comparable
- LFM2.5-24B-A2B public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 24 (Unranked · 3 rankable rows)

| Benchmark | LFM2.5-24B-A2B | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| MATH-500 | 96.0% | 88.8% | LFM2.5-24B-A2B |
| AIME 2025 | Coming soon | 42.5% | Coming soon |
| AIME26 | Coming soon | 50.0% | Coming soon |

## FAQ

### Which is better overall, LFM2.5-24B-A2B or LFM2.5-8B-A1B?

LFM2.5-24B-A2B has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between LFM2.5-24B-A2B and LFM2.5-8B-A1B?

The widest category gap is in instruction following, where the averages are 75.6 for LFM2.5-24B-A2B and 36.5 for LFM2.5-8B-A1B.

### How many benchmarks does LFM2.5-24B-A2B cover on BenchLM?

LFM2.5-24B-A2B currently has 13 sourced benchmark scores on BenchLM.

### How many benchmarks does LFM2.5-8B-A1B cover on BenchLM?

LFM2.5-8B-A1B currently has 7 sourced benchmark scores on BenchLM.

## Related Comparisons

- [LFM2.5-24B-A2B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-lfm2-5-24b-a2b)
- [LFM2.5-8B-A1B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-lfm2-5-8b-a1b)
- [LFM2.5-24B-A2B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-lfm2-5-24b-a2b)
- [LFM2.5-8B-A1B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-lfm2-5-8b-a1b)

## Explore More

- [LFM2.5-24B-A2B profile](/models/lfm2-5-24b-a2b)
- [LFM2.5-8B-A1B profile](/models/lfm2-5-8b-a1b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)