Inference
EN
LiquidAI

LFM2.5-24B-A2B

LFM2.5-24B-A2B is a reasoning model from LiquidAI. 11 benchmarks count toward its index, in 5 categories.

  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-10
RankedEnough results for an index.
IndexAll categories, out of 100.39.8±7.9Median 51.0
CoverageIndex weight that has results.70%
SpeedOutput tokens per second.280/sMedian 67/s
First tokenSeconds to the first output token.0.3 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.05Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.70Median $2.55
ContextMaximum tokens in one request.128KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
liquid/lfm-2.5-24b-a2b
Max outputMaximum output tokens per request.
8K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.025
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Run locally

23.97B parameters
16-bit
51.3 GB
8-bit
27.7 GB
4-bit
16.3 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 24 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.4 counted32.0196 / 218
CodingCode writing and repair.2 counted38.7182 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted38.6204 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.2 counted58.416 / 63
MathMath problems.1 counted45.6—

Results

11 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Instruction-Following EvalInstructionAbove fitFar above this model's index.96.8%1 / 70
Berkeley Function Calling Leaderboard v4Agentic65.0%12 / 26
MATH-500 Problem SetMath96.0%14 / 27
Instruction Following BenchmarkInstructionAbove fitFar above this model's index.74.7%30 / 57
Graduate-Level Google-Proof Q&AKnowledge74.4%84 / 141
PinchBenchAgentic83.2%7 / 10
Scientific Code BenchmarkCoding32.7%28 / 35
GPQA Diamond · BenchLMKnowledge74.4%69 / 84
Software Engineering Benchmark VerifiedCoding51.0%95 / 114
AutomationBenchAgentic27.7%29 / 32
τ³-Bench Tool-Agent-User EvaluationAgentic8.0%31 / 32
Humanity's Last ExamKnowledge7.4%75 / 77
WebArena-Verified Browser Agent BenchmarkAgentic26.8%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuse

History

5 releases
Index41.2 → 39.8
23 Oct 202612 Nov 2026
Output / 1M$0.70 → $0.70
23 Oct 202612 Nov 2026

Questions

How much does LFM2.5-24B-A2B cost?
$0.05 per 1M input tokens, $0.70 per 1M output tokens.
How good is LFM2.5-24B-A2B?
Its index is 39.8 out of 100. That is place 208 of 283 ranked models.
What is LFM2.5-24B-A2B best at?
Instruction: 58.4 out of 100, place 16 of 63.
How fast is LFM2.5-24B-A2B?
280 output tokens per second, 0.3 s to the first token.
What is the context window of LFM2.5-24B-A2B?
128K tokens.
Is LFM2.5-24B-A2B open source?
Yes. Its weights are published.
When was LFM2.5-24B-A2B released?
October 2026.

Badge

LFM2.5-24B-A2B on Inference360: place 208 of 283, index 39.8
HTML
<a href="https://inference360.ai/models/lfm2-5-24b-a2b"><img src="https://inference360.ai/badges/lfm2-5-24b-a2b.svg" alt="LFM2.5-24B-A2B on Inference360: place 208 of 283, index 39.8" height="20"></a>
Markdown
[![LFM2.5-24B-A2B on Inference360: place 208 of 283, index 39.8](https://inference360.ai/badges/lfm2-5-24b-a2b.svg)](https://inference360.ai/models/lfm2-5-24b-a2b)

Compare with

Kimi K239.6o3-mini40.0LFM3-1.7B41.5LFM2.5-2.6B29.3dots3-note Preview63.4

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from LiquidAI

All models
d1-ultraUnrankedd1-3BUnrankedd1-omni-600MUnrankedLFM3-1.7B41.5d1-2BUnranked