Models Agents EvalsIndustry

AgMoDB by @mistakeknot

o3-mini (high) | AgMoDB

o3-mini (high)

January 31, 2025Last synced Apr 7, 2026, 4:00 PM200K context

Blended Price

$1.93/M

Input Price

$1.10/M

Output Price

$4.40/M

Speed

166 tok/s

TTFT

24.00s

Benchmark Scores

Intelligence Index

External Benchmarks

Aider Polyglot

How o3-mini (high) Compares

Axes

X Axis

Y Axis

Bubble Size

Filters

Blended Price (USD)$0.00 – $30.0

AgMoBench Overall≥ 3.5

Providers

ai21-labsalibabaanthropicawsazurebaiducoheredeepseek

Show quadrants

anthropic

openai

google

meta

mistral

nvidia

kimi

xai

azure

deepseek

aws

cohere

baidu

ai21-labs

zai

reka-ai

xiaomi

alibaba

minimax

ibm

Bubble size = Context Window

16384.00

2000000.00

Compare with other models

25.2

Coding Index

17.3

Math Index

—

MMLU Pro

0.8 / 100

GPQA Diamond

0.8 / 100

HLE

0.1 / 100

LiveCodeBench

0.7 / 100

SciCode

0.4 / 100

MATH-500

1.0 / 100

AIME

0.9 / 30

AIME 2025

— / 30

IFBench

0.7 / 100

LCR

0.4 / 100

Terminal-Bench Hard

0.1 / 100

τ²-Bench

0.3 / 100

aider

60.4 / 100

ARC-AGI-1arc_agi

34.5 / 100

ARC-AGI-1 Cost per Taskarc_agi

0.4

ARC-AGI-2arc_agi

3.0 / 100

ARC-AGI-2 Cost per Taskarc_agi

0.5

ARC-AGI-1benchmark_matrix

34.5 / 100

ARC-AGI-2benchmark_matrix

3.0 / 100

AIME 2024benchmark_matrix

87.3

AIME 2025 (Matrix)benchmark_matrix

86.5

Arena-Hard Autobenchmark_matrix

43.0

Chatbot Arena ELO (Matrix)benchmark_matrix

1364.0

Codeforces Ratingbenchmark_matrix

2130.0

GPQA Diamond (Matrix)benchmark_matrix

79.7

HLE (Matrix)benchmark_matrix

13.0

HMMT Feb 2025benchmark_matrix

50.0

HumanEvalbenchmark_matrix

97.6

IFEvalbenchmark_matrix

88.0

LiveCodeBench (Matrix)benchmark_matrix

74.1

MATH-500 (Matrix)benchmark_matrix

97.9

MMLUbenchmark_matrix

86.9

MMLU-Pro (Matrix)benchmark_matrix

80.0

SimpleQAbenchmark_matrix

13.8

USAMO 2025benchmark_matrix

2.1

FrontierMathbenchmark_matrix

11.0 / 100

simpleqabenchmark_matrix

13.8

SWE-bench Verifiedbenchmark_matrix

49.3 / 100

AA-Omniscience AccuracyPredicted

37.8 / 100

AA-Omniscience Hallucination RatePredicted

95.6 / 100

AIME 2025Predicted

0.6 / 30

AlpacaEval 2.0 LCPredicted

24.3 / 100

AlpacaEval 2.0 RawPredicted

29.7 / 100

BFCL (Berkeley Function Calling)Predicted

50.0

BigCodeBench CompletePredicted

60.2 / 100

BigCodeBench InstructPredicted

49.9 / 100

AA Intelligence Index (Matrix)Predicted

69.4

AA Long Context Reasoning (Matrix)Predicted

65.5

BrowseCompPredicted

54.9

BRUMO 2025Predicted

69.9

CMIMC 2025Predicted

71.3

CritPtPredicted

0.1

GSM8KPredicted

94.3

HMMT Nov 2025Predicted

56.1

IFBench (Matrix)Predicted

49.3

IMO 2025Predicted

13.4

MathArena Apex 2025Predicted

0.3

MMMU-ProPredicted

82.0

MRCR v2Predicted

85.1

OSWorldPredicted

38.1

SMT 2025Predicted

79.4

SWE-bench ProPredicted

35.0

Tau-Bench Telecom (Matrix)Predicted

95.1

Terminal-Bench 2.0Predicted

9.1

Terminal-Bench 1.0Predicted

29.3

Video-MMUPredicted

75.8

browsecompPredicted

50.4

BullshitBenchPredicted

14.8 / 100

Apex AgentsPredicted

2.0

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.7

DeepResearchBenchPredicted

0.3

GdpvalPredicted

0.2

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

14.4

HellaSwagPredicted

3.0

HlePredicted

0.1

METR Time HorizonsPredicted

2.2

PIQAPredicted

0.9

PosttrainbenchPredicted

50.1

SimpleQA Verified (Epoch)Predicted

0.3

The Agent CompanyPredicted

2.1

TriviaQAPredicted

4.3

VPCTPredicted

0.4

WinoGrandePredicted

0.9

GAIA Level 1Predicted

71.4

GAIA Level 2Predicted

60.4

GAIA Level 3Predicted

43.7

GAIAPredicted

55.3 / 100

LegalBenchPredicted

82.1 / 100

LiveBench CodingPredicted

64.6 / 100

LiveBench Data AnalysisPredicted

41.9 / 100

LiveBench LanguagePredicted

53.6 / 100

LiveBench MathPredicted

58.4 / 100

LiveBench OverallPredicted

43.8 / 100

LiveBench ReasoningPredicted

40.5 / 100

LongBench v2 EasyPredicted

53.7

LongBench v2 HardPredicted

32.7

LongBench v2Predicted

33.7 / 100

MathVistaPredicted

62.3 / 100

MedQA (USMLE)Predicted

91.2

MLE-benchPredicted

20.4 / 100

MMMUPredicted

76.7 / 100

MMTU Table UnderstandingPredicted

60.7 / 100

MT-BenchPredicted

8.0 / 10

NoLiMa (NIAH)Predicted

94.5 / 100

OCRBench v2Predicted

86.9 / 100

Open LLM AveragePredicted

16.4 / 100

Open LLM: BBHPredicted

43.8 / 100

Open LLM: GPQAPredicted

29.2 / 100

Open LLM: IFEvalPredicted

59.1 / 100

Open LLM: MATH Level 5Predicted

11.8 / 100

Open LLM: MMLU-PROPredicted

26.8 / 100

Open LLM: MUSRPredicted

39.7 / 100

RE-BenchPredicted

1.5

tau-bench RetailPredicted

71.9 / 100

Vectara Factual ConsistencyPredicted

93.1 / 100

Vectara Hallucination RatePredicted

6.9 / 100

WebArenaPredicted

16.5 / 100

WildBenchPredicted

51.5

Aider Polyglotepoch_ai

0.1

Arc Agi 2epoch_ai

0.0

CAD-Evalepoch_ai

5.5

Chess Puzzlesepoch_ai

0.2

CyBenchepoch_ai

0.2

Epoch Capabilities Indexepoch_ai

141.6

FictionLiveBenchepoch_ai

0.4

GSOepoch_ai

0.0

Lech Mazur Writingepoch_ai

6.2

OTIS Mock AIME 2024–2025epoch_ai

0.6

SimpleBenchsimplebench

22.8 / 100

simpleqasimpleqa

13.8

SWE-bench Liteswebench

30.3 / 100

SWE-bench Verifiedswebench

42.4 / 100

WeirdMLweirdml

43.7 / 100