# Celeris-1 vs LFM2.5-8B-A1B

> Side-by-side benchmark comparison for Celeris-1 and LFM2.5-8B-A1B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/celeris-1-vs-lfm2-5-8b-a1b
- Last updated: September 4, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Celeris-1 and LFM2.5-8B-A1B share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- LFM2.5-8B-A1B has the lower published output-token price.

## Model Snapshot

| Property | Celeris-1 | LFM2.5-8B-A1B |
|----------|----------|----------|
| Creator | Celeris | LiquidAI |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 128K | 128K |
| Independent public score (not head-to-head) | null | 41.42 |
| Benchmarks Covered | 4 | 7 |
| Pricing (input/output) | $0.20 / $0.70 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 45.5 (Estimated · #93/151)

| Benchmark | Celeris-1 | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| BFCL v4 | Coming soon | 49.7% | Coming soon |
| τ²-bench results | Coming soon | 88.1% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 45 (Estimated · #112/183)

### Reasoning

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: 47.8 (Unranked · 3 rankable rows)
- LFM2.5-8B-A1B public-lane score: 21 (Unranked · 2 rankable rows)

| Benchmark | Celeris-1 | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| DROP | 81.4% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 34.3 (Supported · #168/181)

| Benchmark | Celeris-1 | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 75.9% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 44.7 (#92/120)

| Benchmark | Celeris-1 | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 80.8% | 91.8% | LFM2.5-8B-A1B |
| IFBench | Coming soon | 56.5% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Celeris-1 public-lane score: Coming soon
- LFM2.5-8B-A1B public-lane score: 27.7 (Unranked · 3 rankable rows)

| Benchmark | Celeris-1 | LFM2.5-8B-A1B | Winner |
|-----------|-----------|-----------|--------|
| GSM8K | 93.7% | Coming soon | Coming soon |
| MATH-500 | Coming soon | 88.8% | Coming soon |
| AIME 2025 | Coming soon | 42.5% | Coming soon |
| AIME26 | Coming soon | 50.0% | Coming soon |

## FAQ

### Is there enough evidence to pick between Celeris-1 and LFM2.5-8B-A1B?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Celeris-1 vs Claude Fable 5.1](/compare/celeris-1-vs-claude-fable-5-1)
- [LFM2.5-8B-A1B vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-lfm2-5-8b-a1b)
- [Celeris-1 vs GPT-6 Astra](/compare/celeris-1-vs-gpt-6-astra)
- [LFM2.5-8B-A1B vs GPT-6 Astra](/compare/gpt-6-astra-vs-lfm2-5-8b-a1b)

## Explore More

- [Celeris-1 profile](/models/celeris-1)
- [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)