Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Mercury 2 | AgMoDB

Mercury 2

February 20, 2026Last synced Apr 7, 2026, 4:00 PM128K context

Blended Price

$0.38/M

Input Price

$0.25/M

Output Price

$0.75/M

Speed

927 tok/s

TTFT

4.47s

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Mercury 2 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

32.8

Coding Index

30.6

Math Index

—

MMLU Pro

— / 100

GPQA Diamond

0.8 / 100

HLE

0.2 / 100

LiveCodeBench

— / 100

SciCode

0.4 / 100

MATH-500

— / 100

AIME

— / 30

AIME 2025

— / 30

IFBench

0.7 / 100

LCR

0.4 / 100

Terminal-Bench Hard

0.3 / 100

τ²-Bench

0.7 / 100

Predicted

44.0 / 100

AA-Omniscience Hallucination RatePredicted

97.2 / 100

Aider PolyglotPredicted

80.6 / 100

AIMEPredicted

0.4 / 30

AIME 2025Predicted

0.9 / 30

AlpacaEval 2.0 LCPredicted

25.7 / 100

AlpacaEval 2.0 RawPredicted

20.0 / 100

ARC-AGI-1Predicted

74.0 / 100

ARC-AGI-1 Cost per TaskPredicted

0.5

ARC-AGI-2Predicted

24.2 / 100

ARC-AGI-2 Cost per TaskPredicted

1.1

BFCL (Berkeley Function Calling)Predicted

53.3

BigCodeBench CompletePredicted

46.0 / 100

BigCodeBench InstructPredicted

36.6 / 100

AA Intelligence Index (Matrix)Predicted

63.0

AA Long Context Reasoning (Matrix)Predicted

74.9

AIME 2024Predicted

98.2

AIME 2025 (Matrix)Predicted

99.6

Arena-Hard AutoPredicted

81.1

BrowseCompPredicted

73.4

BRUMO 2025Predicted

98.7

CMIMC 2025Predicted

90.4

CritPtPredicted

4.8

GPQA Diamond (Matrix)Predicted

88.0

GSM8KPredicted

95.5

HLE (Matrix)Predicted

34.1

HMMT Feb 2025Predicted

92.1

HMMT Nov 2025Predicted

92.5

HumanEvalPredicted

92.5

IFBench (Matrix)Predicted

61.3

IFEvalPredicted

91.1

IMO 2025Predicted

37.2

LiveCodeBench (Matrix)Predicted

81.6

MATH-500 (Matrix)Predicted

98.2

MathArena Apex 2025Predicted

4.2

MMLUPredicted

89.9

MMLU-Pro (Matrix)Predicted

85.1

MMMU-ProPredicted

81.0

MRCR v2Predicted

79.8

OSWorldPredicted

54.7

SimpleQAPredicted

52.9

SMT 2025Predicted

91.3

SWE-bench ProPredicted

46.5

Tau-Bench Telecom (Matrix)Predicted

98.1

Terminal-Bench 2.0Predicted

49.2

Terminal-Bench 1.0Predicted

38.2

USAMO 2025Predicted

23.7

Video-MMUPredicted

86.2

browsecompPredicted

72.3

BullshitBenchPredicted

37.7 / 100

Aider PolyglotPredicted

0.1

Apex AgentsPredicted

2.9

Arc Agi 2Predicted

0.0

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.7

CAD-EvalPredicted

2.9

Chess PuzzlesPredicted

0.2

CyBenchPredicted

0.5

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.8

GdpvalPredicted

0.4

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

3.0

GSOPredicted

0.1

HellaSwagPredicted

0.0

HlePredicted

0.2

Lech Mazur WritingPredicted

8.4

METR Time HorizonsPredicted

12.9

OTIS Mock AIME 2024–2025Predicted

0.8

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.5

The Agent CompanyPredicted

2.7

TriviaQAPredicted

13.4

VPCTPredicted

0.6

WinoGrandePredicted

0.8

FrontierMathPredicted

27.0 / 100

GAIA Level 1Predicted

77.1

GAIA Level 2Predicted

60.5

GAIA Level 3Predicted

64.9

GAIAPredicted

61.6 / 100

LegalBenchPredicted

79.6 / 100

LiveBench CodingPredicted

73.8 / 100

LiveBench Data AnalysisPredicted

61.3 / 100

LiveBench LanguagePredicted

72.7 / 100

LiveBench MathPredicted

79.4 / 100

LiveBench OverallPredicted

65.9 / 100

LiveBench ReasoningPredicted

68.8 / 100

LiveCodeBenchPredicted

0.7 / 100

LongBench v2 EasyPredicted

54.5

LongBench v2 HardPredicted

45.0

LongBench v2Predicted

40.9 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

69.1 / 100

MedQA (USMLE)Predicted

94.3

MLE-benchPredicted

53.6 / 100

MMLU ProPredicted

0.8 / 100

MMMUPredicted

81.8 / 100

MMTU Table UnderstandingPredicted

63.7 / 100

MT-BenchPredicted

7.9 / 10

NoLiMa (NIAH)Predicted

93.6 / 100

OCRBench v2Predicted

82.6 / 100

Open LLM AveragePredicted

17.1 / 100

Open LLM: BBHPredicted

45.7 / 100

Open LLM: GPQAPredicted

28.8 / 100

Open LLM: IFEvalPredicted

36.3 / 100

Open LLM: MATH Level 5Predicted

7.2 / 100

Open LLM: MMLU-PROPredicted

29.6 / 100

Open LLM: MUSRPredicted

40.1 / 100

RE-BenchPredicted

99.4

SimpleBenchPredicted

56.6 / 100

simpleqaPredicted

49.7

SWE-bench LitePredicted

50.4 / 100

SWE-bench VerifiedPredicted

75.3 / 100

tau-bench RetailPredicted

87.4 / 100

WebArenaPredicted

0.8 / 100

WildBenchPredicted

42.0

Vectara Factual Consistencyvectara_hallucination

87.7 / 100

Vectara Hallucination Ratevectara_hallucination

12.3 / 100

WeirdMLweirdml

43.2 / 100