AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Models

LFM2.5-1.2B-Thinking

January 20, 2026Last synced Nov 5, 2026, 12:18 AM

Blended Price

Free/M

Input Price

Free/M

Output Price

Free/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index
—
Coding Index
—
Math Index
—
MMLU Pro
— / 100
GPQA Diamond
33.9 / 100
HLE
6.2 / 100
LiveCodeBench
— / 100
SciCode
— / 100
MATH-500
— / 100
AIME
— / 30
AIME 2025
— / 30
IFBench
41.8 / 100
LCR
0.0 / 100
Terminal-Bench Hard
0.0 / 100
τ²-Bench
19.6 / 100

Performance Radar

LFM2.5-1.2B-Thinking
Field Average

Hidden, no data: AgMoBench Agentic, AgMoBench Robustness, Output Speed

External Benchmarks

AA-Omniscience Hallucination Rateaa_omniscience
96.9 / 100
AIME 2025 (Matrix)benchmark_matrix
31.7
GPQA Diamond (Matrix)benchmark_matrix
37.9
HumanEvalbenchmark_matrix
55.0
IFEvalbenchmark_matrix
88.4
LiveCodeBench (Matrix)benchmark_matrix
22.0
MATH-500 (Matrix)benchmark_matrix
88.0
MMLUbenchmark_matrix
52.0
MMLU-Pro (Matrix)benchmark_matrix
49.6
AA-Omniscience AccuracyPredicted
49.3 / 100
Aider PolyglotPredicted
15.2 / 100
AIMEPredicted
0.0 / 30
AIME 2025Predicted
0.0 / 30
AlpacaEval 2.0 LCPredicted
19.7 / 100
AlpacaEval 2.0 RawPredicted
15.8 / 100
ARC-AGI-1Predicted
39.8 / 100
ARC-AGI-1 Cost per TaskPredicted
0.3
ARC-AGI-2Predicted
25.0 / 100
ARC-AGI-2 Cost per TaskPredicted
0.7
BFCL (Berkeley Function Calling)Predicted
22.7
BigCodeBench CompletePredicted
29.1 / 100
BigCodeBench InstructPredicted
22.9 / 100
AA Intelligence Index (Matrix)Predicted
51.6
AA Long Context Reasoning (Matrix)Predicted
75.9
AIME 2024Predicted
28.2
Arena-Hard AutoPredicted
26.7
BrowseCompPredicted
84.8
BRUMO 2025Predicted
99.2
CMIMC 2025Predicted
91.6
CritPtPredicted
5.6
GSM8KPredicted
70.2
HLE (Matrix)Predicted
28.0
HMMT Feb 2025Predicted
62.5
HMMT Nov 2025Predicted
93.6
IFBench (Matrix)Predicted
29.4
IMO 2025Predicted
36.4
MathArena Apex 2025Predicted
11.5
MMMU-ProPredicted
76.0
MRCR v2Predicted
80.5
OSWorld (Unversioned Matrix Import)Predicted
75.6 / 100
SimpleQAPredicted
42.5
SMT 2025Predicted
91.4
SWE-bench ProPredicted
54.3
Tau-Bench Telecom (Matrix)Predicted
98.7
Terminal-Bench 2.0Predicted
67.2
Terminal-Bench 1.0Predicted
26.3
USAMO 2025Predicted
8.9
Video-MMUPredicted
84.1
browsecompPredicted
86.5
BullshitBenchPredicted
48.0 / 100
Aider PolyglotPredicted
0.0
Apex AgentsPredicted
4.1
Arc Agi 2Predicted
0.1
BALROGPredicted
0.0
BIG-Bench HardPredicted
3.0
BoolQPredicted
0.8
CAD-EvalPredicted
8.4
Chess PuzzlesPredicted
0.3
CyBenchPredicted
0.1
DeepResearchBenchPredicted
0.4
FictionLiveBenchPredicted
0.4
GdpvalPredicted
0.5
GeoBenchPredicted
0.0
GSM8K (Epoch)Predicted
6.0
GSOPredicted
0.3
HellaSwagPredicted
0.1
HlePredicted
0.1
Lech Mazur WritingPredicted
6.9
METR Time HorizonsPredicted
4.9
OTIS Mock AIME 2024–2025Predicted
0.0
PIQAPredicted
0.8
PosttrainbenchPredicted
0.0
SimpleQA Verified (Epoch)Predicted
0.5
The Agent CompanyPredicted
0.8
TriviaQAPredicted
7.7
VPCTPredicted
0.5
WinoGrandePredicted
0.7
FrontierMathPredicted
36.0 / 100
GAIA Level 1Predicted
6.9
GAIA Level 2Predicted
0.6
GAIA Level 3Predicted
0.0
GAIAPredicted
4.1 / 100
LegalBenchPredicted
27.4 / 100
LiveBench CodingPredicted
65.9 / 100
LiveBench Data AnalysisPredicted
64.6 / 100
LiveBench LanguagePredicted
76.5 / 100
LiveBench MathPredicted
61.0 / 100
LiveBench OverallPredicted
68.8 / 100
LiveBench ReasoningPredicted
71.5 / 100
LiveCodeBenchPredicted
0.1 / 100
LongBench v2 EasyPredicted
28.9
LongBench v2 HardPredicted
25.0
LongBench v2Predicted
23.3 / 100
MATH-500Predicted
0.3 / 100
MathVistaPredicted
18.6 / 100
MedQA (USMLE)Predicted
56.4
MLE-bench (Original)Predicted
52.0 / 100
MMLU ProPredicted
0.4 / 100
MMMUPredicted
53.3 / 100
MMTU Table UnderstandingPredicted
47.5 / 100
MT-BenchPredicted
7.7 / 10
NoLiMa (NIAH)Predicted
91.6 / 100
OCRBench v2Predicted
56.2 / 100
Open LLM AveragePredicted
21.0 / 100
Open LLM: BBHPredicted
45.5 / 100
Open LLM: GPQAPredicted
28.1 / 100
Open LLM: IFEvalPredicted
63.0 / 100
Open LLM: MATH Level 5Predicted
10.9 / 100
Open LLM: MMLU-PROPredicted
29.2 / 100
Open LLM: MUSRPredicted
38.0 / 100
RE-BenchPredicted
99.5
SimpleBenchPredicted
36.6 / 100
simpleqaPredicted
32.2
SWE-bench LitePredicted
7.9 / 100
SWE-bench VerifiedPredicted
41.1 / 100
tau-bench RetailPredicted
90.4 / 100
Vectara Factual ConsistencyPredicted
88.8 / 100
Vectara Hallucination RatePredicted
11.2 / 100
WebArenaPredicted
15.6 / 100
WeirdMLPredicted
34.6 / 100
WildBenchPredicted
30.0

How LFM2.5-1.2B-Thinking Compares

Axes

Filters

$0.00 – $67.5
≥ 1.4

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu
openai
zai
meta
nvidia
xai
upstage
deepseek
alibaba
mistral
nous-research
aws
google
anthropic
xiaomi
stepfun
kimi
reflection
minimax
azure
inclusionai
reka-ai
cohere
bytedance_seed
inception
tencent
thinking-machines
Bubble size = Context Window
8191.00
2000000.00
Compare with other models