Qwen: Qwen3 8B

Last synced Apr 7, 2026, 2:03 PM32K context

Blended Price

$0.14/M

Input Price

$0.050/M

Output Price

$0.40/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

External Benchmarks

AIME 2024benchmark_matrix

How Qwen: Qwen3 8B 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

AIME 2025 (Matrix)benchmark_matrix

67.3

Arena-Hard Autobenchmark_matrix

76.0

Codeforces Ratingbenchmark_matrix

1850.0

GPQA Diamond (Matrix)benchmark_matrix

63.3

GSM8Kbenchmark_matrix

89.8

HumanEvalbenchmark_matrix

82.0

IFBench (Matrix)benchmark_matrix

35.0

IFEvalbenchmark_matrix

80.0

LiveCodeBench (Matrix)benchmark_matrix

48.0

MATH-500 (Matrix)benchmark_matrix

94.0

MMLUbenchmark_matrix

76.9

MMLU-Pro (Matrix)benchmark_matrix

56.7

AA-Omniscience AccuracyPredicted

38.7 / 100

AA-Omniscience Hallucination RatePredicted

93.9 / 100

Aider PolyglotPredicted

22.7 / 100

AIMEPredicted

0.5 / 30

AIME 2025Predicted

0.2 / 30

AlpacaEval 2.0 LCPredicted

50.3 / 100

AlpacaEval 2.0 RawPredicted

39.4 / 100

ARC-AGI-1Predicted

1.7 / 100

ARC-AGI-1 Cost per TaskPredicted

0.0

ARC-AGI-2Predicted

0.0 / 100

ARC-AGI-2 Cost per TaskPredicted

0.0

BigCodeBench CompletePredicted

60.9 / 100

BigCodeBench InstructPredicted

50.7 / 100

AA Intelligence Index (Matrix)Predicted

68.9

AA Long Context Reasoning (Matrix)Predicted

68.8

BrowseCompPredicted

51.4

BRUMO 2025Predicted

73.0

CMIMC 2025Predicted

59.3

HLE (Matrix)Predicted

18.3

HMMT Feb 2025Predicted

31.6

HMMT Nov 2025Predicted

87.1

IMO 2025Predicted

7.9

MathArena Apex 2025Predicted

0.4

MMMU-ProPredicted

81.0

MRCR v2Predicted

72.6

OSWorldPredicted

29.8

SimpleQAPredicted

16.5

SMT 2025Predicted

71.4

SWE-bench ProPredicted

32.0

Tau-Bench Telecom (Matrix)Predicted

93.4

Terminal-Bench 2.0Predicted

11.7

Terminal-Bench 1.0Predicted

11.3

USAMO 2025Predicted

4.7

Video-MMUPredicted

80.2

browsecompPredicted

47.1

BullshitBenchPredicted

9.1 / 100

Aider PolyglotPredicted

0.0

Apex AgentsPredicted

1.9

Arc Agi 2Predicted

0.0

BIG-Bench HardPredicted

3.0

CAD-EvalPredicted

6.3

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.1

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.3

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

40.7

HellaSwagPredicted

43.1

Lech Mazur WritingPredicted

7.0

METR Time HorizonsPredicted

0.1

OTIS Mock AIME 2024–2025Predicted

0.1

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.2

The Agent CompanyPredicted

1.4

TriviaQAPredicted

2.1

WinoGrandePredicted

0.8

FrontierMathPredicted

8.5 / 100

GAIA Level 1Predicted

41.5

GAIA Level 2Predicted

44.3

GAIA Level 3Predicted

0.9

GAIAPredicted

27.6 / 100

GPQA DiamondPredicted

0.5 / 100

HLEPredicted

0.0 / 100

IFBenchPredicted

0.3 / 100

LCRPredicted

0.0 / 100

LegalBenchPredicted

89.0 / 100

LiveBench CodingPredicted

61.0 / 100

LiveBench Data AnalysisPredicted

33.6 / 100

LiveBench LanguagePredicted

41.2 / 100

LiveBench MathPredicted

49.1 / 100

LiveBench OverallPredicted

35.2 / 100

LiveBench ReasoningPredicted

26.3 / 100

LiveCodeBenchPredicted

0.4 / 100

LongBench v2 EasyPredicted

45.2

LongBench v2 HardPredicted

36.6

LongBench v2Predicted

36.3 / 100

MATH-500Predicted

0.9 / 100

MathVistaPredicted

57.1 / 100

MLE-benchPredicted

11.5 / 100

MMLU ProPredicted

0.7 / 100

MMMUPredicted

67.3 / 100

MMTU Table UnderstandingPredicted

48.9 / 100

MT-BenchPredicted

7.9 / 10

NoLiMa (NIAH)Predicted

94.4 / 100

OCRBench v2Predicted

79.9 / 100

Open LLM AveragePredicted

45.2 / 100

Open LLM: BBHPredicted

69.9 / 100

Open LLM: GPQAPredicted

36.1 / 100

Open LLM: IFEvalPredicted

75.3 / 100

Open LLM: MATH Level 5Predicted

49.8 / 100

Open LLM: MMLU-PROPredicted

56.4 / 100

Open LLM: MUSRPredicted

45.8 / 100

RE-BenchPredicted

0.0

SciCodePredicted

0.3 / 100

SimpleBenchPredicted

24.5 / 100

simpleqaPredicted

17.1

SWE-bench LitePredicted

15.4 / 100

SWE-bench VerifiedPredicted

32.1 / 100

τ²-BenchPredicted

0.2 / 100

tau-bench RetailPredicted

70.4 / 100

Terminal-Bench HardPredicted

0.0 / 100

WebArenaPredicted

19.3 / 100

WeirdMLPredicted

22.6 / 100

WildBenchPredicted

47.4

BFCL (Berkeley Function Calling)bfcl

42.6

EQ-Bench 3eqbench

1251.0

HuggingFace Downloads (30d)hf-downloads

8937175.0

HuggingFace Likeshf-downloads

1029.0

Vectara Factual Consistencyvectara_hallucination

95.2 / 100

Vectara Hallucination Ratevectara_hallucination

4.8 / 100