Reka Edge

Last synced Apr 7, 2026, 2:03 PM16K context

Blended Price

$0.100/M

Input Price

$0.100/M

Output Price

$0.100/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How Reka Edge 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

GPQA Diamond

— / 100

LiveCodeBench

— / 100

Terminal-Bench Hard

— / 100

τ²-Bench

— / 100

AA-Omniscience Hallucination RatePredicted

96.7 / 100

Aider PolyglotPredicted

8.7 / 100

AIMEPredicted

0.0 / 30

AIME 2025Predicted

0.0 / 30

AlpacaEval 2.0 LCPredicted

16.7 / 100

AlpacaEval 2.0 RawPredicted

13.7 / 100

ARC-AGI-1Predicted

44.7 / 100

ARC-AGI-1 Cost per TaskPredicted

0.3

ARC-AGI-2Predicted

60.8 / 100

ARC-AGI-2 Cost per TaskPredicted

0.4

BFCL (Berkeley Function Calling)Predicted

17.3

BigCodeBench CompletePredicted

23.3 / 100

BigCodeBench InstructPredicted

18.3 / 100

AA Intelligence Index (Matrix)Predicted

47.1

AA Long Context Reasoning (Matrix)Predicted

76.9

AIME 2024Predicted

12.2

AIME 2025 (Matrix)Predicted

58.4

Arena-Hard AutoPredicted

7.7

BrowseCompPredicted

88.7

BRUMO 2025Predicted

99.6

CMIMC 2025Predicted

93.6

CritPtPredicted

10.0

GPQA Diamond (Matrix)Predicted

32.2

HLE (Matrix)Predicted

30.5

HMMT Feb 2025Predicted

58.0

HMMT Nov 2025Predicted

94.3

HumanEvalPredicted

59.8

IFBench (Matrix)Predicted

30.1

IFEvalPredicted

68.2

IMO 2025Predicted

42.1

LiveCodeBench (Matrix)Predicted

21.9

MATH-500 (Matrix)Predicted

76.3

MathArena Apex 2025Predicted

20.1

MMLU-Pro (Matrix)Predicted

48.0

MMMU-ProPredicted

74.3

MRCR v2Predicted

81.5

OSWorldPredicted

82.3

SimpleQAPredicted

44.8

SMT 2025Predicted

92.8

SWE-bench ProPredicted

58.6

Tau-Bench Telecom (Matrix)Predicted

99.0

Terminal-Bench 2.0Predicted

76.9

Terminal-Bench 1.0Predicted

26.9

USAMO 2025Predicted

7.9

Video-MMUPredicted

83.3

browsecompPredicted

90.7

BullshitBenchPredicted

41.6 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

4.8

Arc Agi 2Predicted

60.1

BIG-Bench HardPredicted

3.0

CAD-EvalPredicted

10.5

Chess PuzzlesPredicted

0.4

CyBenchPredicted

0.1

DeepResearchBenchPredicted

0.4

FictionLiveBenchPredicted

0.3

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

0.0

HellaSwagPredicted

0.0

Lech Mazur WritingPredicted

6.7

METR Time HorizonsPredicted

6.3

OTIS Mock AIME 2024–2025Predicted

0.0

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.5

The Agent CompanyPredicted

0.6

TriviaQAPredicted

8.2

WinoGrandePredicted

0.6

FrontierMathPredicted

43.4 / 100

GAIA Level 1Predicted

2.7

GAIA Level 2Predicted

0.1

GAIA Level 3Predicted

0.0

GAIAPredicted

1.7 / 100

GPQA DiamondPredicted

0.2 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.2 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

14.3 / 100

LiveBench CodingPredicted

78.1 / 100

LiveBench Data AnalysisPredicted

68.8 / 100

LiveBench LanguagePredicted

80.4 / 100

LiveBench MathPredicted

86.2 / 100

LiveBench OverallPredicted

73.0 / 100

LiveBench ReasoningPredicted

76.7 / 100

LiveCodeBenchPredicted

0.0 / 100

LongBench v2 EasyPredicted

23.4

LongBench v2 HardPredicted

20.3

LongBench v2Predicted

19.2 / 100

MATH-500Predicted

0.1 / 100

MathVistaPredicted

40.4 / 100

MedQA (USMLE)Predicted

41.9

MLE-benchPredicted

58.4 / 100

MMLU ProPredicted

0.2 / 100

MMTU Table UnderstandingPredicted

43.9 / 100

MT-BenchPredicted

7.5 / 10

NoLiMa (NIAH)Predicted

76.6 / 100

OCRBench v2Predicted

46.1 / 100

Open LLM AveragePredicted

19.4 / 100

Open LLM: BBHPredicted

42.2 / 100

Open LLM: GPQAPredicted

27.0 / 100

Open LLM: IFEvalPredicted

65.8 / 100

Open LLM: MATH Level 5Predicted

9.2 / 100

Open LLM: MMLU-PROPredicted

26.2 / 100

Open LLM: MUSRPredicted

36.7 / 100

RE-BenchPredicted

99.9

SciCodePredicted

0.0 / 100

SimpleBenchPredicted

36.0 / 100

simpleqaPredicted

31.6

SWE-bench LitePredicted

4.8 / 100

SWE-bench VerifiedPredicted

36.0 / 100

τ²-BenchPredicted

0.0 / 100

tau-bench RetailPredicted

92.2 / 100

Terminal-Bench HardPredicted

0.0 / 100

Vectara Factual ConsistencyPredicted

91.8 / 100

Vectara Hallucination RatePredicted

8.2 / 100

WebArenaPredicted

0.0 / 100

WeirdMLPredicted

12.5 / 100

WildBenchwildbench

23.2