WizardLM-2 8x22B

Last synced Apr 7, 2026, 2:04 PM66K context

Blended Price

$0.62/M

Input Price

$0.62/M

Output Price

$0.62/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AA-Omniscience Accuracy

How WizardLM-2 8x22B 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

95.5 / 100

Aider PolyglotPredicted

54.3 / 100

AIMEPredicted

0.8 / 30

AIME 2025Predicted

0.7 / 30

AlpacaEval 2.0 LCPredicted

38.2 / 100

AlpacaEval 2.0 RawPredicted

29.8 / 100

ARC-AGI-1Predicted

9.5 / 100

ARC-AGI-1 Cost per TaskPredicted

0.0

ARC-AGI-2Predicted

0.0 / 100

ARC-AGI-2 Cost per TaskPredicted

0.1

BFCL (Berkeley Function Calling)Predicted

48.8

BigCodeBench CompletePredicted

60.1 / 100

BigCodeBench InstructPredicted

49.8 / 100

AA Intelligence Index (Matrix)Predicted

69.3

AA Long Context Reasoning (Matrix)Predicted

70.5

AIME 2024Predicted

90.7

AIME 2025 (Matrix)Predicted

85.1

Arena-Hard AutoPredicted

81.8

BrowseCompPredicted

54.9

BRUMO 2025Predicted

80.6

CMIMC 2025Predicted

86.0

GPQA Diamond (Matrix)Predicted

78.2

HLE (Matrix)Predicted

65.0

HMMT Feb 2025Predicted

63.8

HMMT Nov 2025Predicted

88.6

HumanEvalPredicted

90.8

IFBench (Matrix)Predicted

44.5

IFEvalPredicted

88.0

IMO 2025Predicted

13.2

LiveCodeBench (Matrix)Predicted

69.9

MATH-500 (Matrix)Predicted

96.9

MathArena Apex 2025Predicted

0.6

MMLU-Pro (Matrix)Predicted

81.7

MMMU-ProPredicted

81.4

MRCR v2Predicted

74.7

OSWorldPredicted

34.8

SimpleQAPredicted

24.4

SMT 2025Predicted

78.5

SWE-bench ProPredicted

34.7

Tau-Bench Telecom (Matrix)Predicted

95.0

Terminal-Bench 2.0Predicted

17.0

Terminal-Bench 1.0Predicted

18.4

USAMO 2025Predicted

9.6

Video-MMUPredicted

86.8

browsecompPredicted

50.5

BullshitBenchPredicted

56.8 / 100

Aider PolyglotPredicted

0.1

Apex AgentsPredicted

2.0

Arc Agi 2Predicted

5.2

BIG-Bench HardPredicted

3.0

CAD-EvalPredicted

4.1

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.2

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.6

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

14.7

HellaSwagPredicted

1.2

Lech Mazur WritingPredicted

7.7

METR Time HorizonsPredicted

0.7

OTIS Mock AIME 2024–2025Predicted

0.5

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.3

The Agent CompanyPredicted

2.1

TriviaQAPredicted

6.8

WinoGrandePredicted

0.9

FrontierMathPredicted

35.6 / 100

GAIA Level 1Predicted

69.8

GAIA Level 2Predicted

58.0

GAIA Level 3Predicted

37.3

GAIAPredicted

53.5 / 100

GPQA DiamondPredicted

0.7 / 100

HLEPredicted

0.1 / 100

IFBenchPredicted

0.5 / 100

LCRPredicted

0.2 / 100

LegalBenchPredicted

91.2 / 100

LiveBench CodingPredicted

64.6 / 100

LiveBench Data AnalysisPredicted

40.8 / 100

LiveBench LanguagePredicted

50.0 / 100

LiveBench MathPredicted

58.2 / 100

LiveBench OverallPredicted

43.6 / 100

LiveBench ReasoningPredicted

37.4 / 100

LiveCodeBenchPredicted

0.6 / 100

LongBench v2 EasyPredicted

53.2

LongBench v2 HardPredicted

48.4

LongBench v2Predicted

38.2 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

60.0 / 100

MedQA (USMLE)Predicted

89.9

MLE-benchPredicted

20.0 / 100

MMLU ProPredicted

0.8 / 100

MMMUPredicted

76.2 / 100

MMTU Table UnderstandingPredicted

52.7 / 100

MT-BenchPredicted

8.0 / 10

NoLiMa (NIAH)Predicted

94.7 / 100

OCRBench v2Predicted

85.9 / 100

RE-BenchPredicted

1.3

SciCodePredicted

0.5 / 100

SimpleBenchPredicted

29.2 / 100

simpleqaPredicted

26.3

SWE-bench LitePredicted

32.8 / 100

SWE-bench VerifiedPredicted

41.2 / 100

τ²-BenchPredicted

0.3 / 100

tau-bench RetailPredicted

75.5 / 100

Terminal-Bench HardPredicted

0.3 / 100

Vectara Factual ConsistencyPredicted

93.2 / 100

Vectara Hallucination RatePredicted

6.8 / 100

WebArenaPredicted

8.8 / 100

WeirdMLPredicted

40.2 / 100

WildBenchPredicted

53.8

Open LLM Averageopen_llm_leaderboard

33.1 / 100

Open LLM: BBHopen_llm_leaderboard

63.8 / 100

Open LLM: GPQAopen_llm_leaderboard

38.2 / 100

Open LLM: IFEvalopen_llm_leaderboard

52.7 / 100

Open LLM: MATH Level 5open_llm_leaderboard

25.0 / 100

Open LLM: MMLU-PROopen_llm_leaderboard

46.0 / 100

Open LLM: MUSRopen_llm_leaderboard

43.9 / 100