LFM2.5-2.6B

LFM2.5-2.6B is a reasoning model from LiquidAI. 15 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.27.5 ±5.7
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.197/s
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change. A free tier is available.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
34.8
CodingCode writing and repair.
22.8
ReasoningLogic problems and puzzles.
25.3
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
27.3
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
34.9
MathMath problems.
19.0

Results

15 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
PinchBenchAgentic68.2%Kilo Code
Claw-EvalAgentic62.9%57.2Bowen Ye et al.
LiveCodeBench v6Coding59.4%31.1LiveCodeBench maintainers
Instruction Following BenchmarkInstruction59.2%34.9Benchmark authors
Berkeley Function Calling Leaderboard v4Agentic56.9%41.5Arcee AI
Artificial Analysis GPQA DiamondKnowledge55.8%25.7Artificial Analysis
American Invitational Mathematics Examination 2025Math51.9%19.0Mathematical Association of America
Artificial Analysis SciCodeCoding14.4%12.9Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge8.4%32.9Artificial Analysis
Artificial Analysis Coding IndexCoding7.7%24.4Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge6.2%31.3Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning5.7%12.2Artificial Analysis
τ³-Bench Tool-Agent-User EvaluationAgentic5.7%5.0Sierra Research
Artificial Analysis Omniscience AccuracyKnowledge4.4%19.3Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
Critical Physics TasksReasoning0.0%38.4Artificial Analysis

15 benchmarks count, from 15 of 16 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors

More from LiquidAI

LFM2.5-8B-A1B32.0LFM2.5-VL-1.6B-Extract19.4LFM2 1.2BUnrankedLFM2 350MUnrankedLFM2 700MUnranked