Models Agents EvalsIndustry

AgMoDB by @mistakeknot

Qwen3 235B A22B 2507 Instruct | AgMoDB

Qwen3 235B A22B 2507 Instruct

July 21, 2025Last synced Apr 7, 2026, 4:00 PM

Blended Price

$1.23/M

Input Price

$0.70/M

Output Price

$2.80/M

Speed

68 tok/s

TTFT

1.05s

Benchmark Scores

Intelligence Index

External Benchmarks

ARC-AGI-1

How Qwen3 235B A22B 2507 Instruct 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

25.0

Coding Index

22.1

Math Index

71.7

MMLU Pro

0.8 / 100

GPQA Diamond

0.8 / 100

HLE

0.1 / 100

LiveCodeBench

0.5 / 100

SciCode

0.4 / 100

MATH-500

1.0 / 100

AIME

0.7 / 30

AIME 2025

0.7 / 30

IFBench

0.5 / 100

LCR

0.3 / 100

Terminal-Bench Hard

0.2 / 100

τ²-Bench

0.3 / 100

arc_agi

11.0 / 100

ARC-AGI-1 Cost per Taskarc_agi

0.0

ARC-AGI-2arc_agi

1.3 / 100

ARC-AGI-2 Cost per Taskarc_agi

0.0

AA-Omniscience AccuracyPredicted

38.7 / 100

AA-Omniscience Hallucination RatePredicted

95.2 / 100

Aider PolyglotPredicted

50.1 / 100

AlpacaEval 2.0 LCPredicted

39.8 / 100

AlpacaEval 2.0 RawPredicted

31.0 / 100

BigCodeBench CompletePredicted

61.5 / 100

BigCodeBench InstructPredicted

51.2 / 100

AA Intelligence Index (Matrix)Predicted

69.0

AA Long Context Reasoning (Matrix)Predicted

69.9

AIME 2024Predicted

88.8

AIME 2025 (Matrix)Predicted

78.2

Arena-Hard AutoPredicted

81.5

BrowseCompPredicted

79.7

BRUMO 2025Predicted

74.8

CMIMC 2025Predicted

67.8

CritPtPredicted

0.1

GPQA Diamond (Matrix)Predicted

76.4

GSM8KPredicted

61.9

HLE (Matrix)Predicted

13.3

HMMT Feb 2025Predicted

58.3

HMMT Nov 2025Predicted

88.1

HumanEvalPredicted

90.2

IFBench (Matrix)Predicted

45.4

IFEvalPredicted

87.5

IMO 2025Predicted

11.5

LiveCodeBench (Matrix)Predicted

67.9

MATH-500 (Matrix)Predicted

96.7

MathArena Apex 2025Predicted

0.5

MMLUPredicted

87.9

MMLU-Pro (Matrix)Predicted

81.4

MMMU-ProPredicted

82.0

MRCR v2Predicted

74.0

OSWorldPredicted

35.3

SimpleQAPredicted

23.9

SMT 2025Predicted

77.2

SWE-bench ProPredicted

33.8

Tau-Bench Telecom (Matrix)Predicted

97.8

Terminal-Bench 2.0Predicted

14.7

Terminal-Bench 1.0Predicted

16.7

USAMO 2025Predicted

8.6

Video-MMUPredicted

86.8

browsecompPredicted

77.9

BullshitBenchPredicted

12.9 / 100

Apex AgentsPredicted

1.9

BALROGPredicted

0.0

BIG-Bench HardPredicted

3.0

BoolQPredicted

0.8

CAD-EvalPredicted

4.3

Chess PuzzlesPredicted

0.1

CyBenchPredicted

0.2

DeepResearchBenchPredicted

0.3

FictionLiveBenchPredicted

0.5

GdpvalPredicted

0.2

GeoBenchPredicted

0.0

GSM8K (Epoch)Predicted

14.0

GSOPredicted

0.0

HellaSwagPredicted

5.8

HlePredicted

0.1

Lech Mazur WritingPredicted

7.6

METR Time HorizonsPredicted

0.5

OTIS Mock AIME 2024–2025Predicted

0.4

PIQAPredicted

0.8

PosttrainbenchPredicted

0.0

SimpleQA Verified (Epoch)Predicted

0.2

The Agent CompanyPredicted

2.0

TriviaQAPredicted

3.6

VPCTPredicted

0.4

WinoGrandePredicted

0.9

FrontierMathPredicted

10.2 / 100

GAIA Level 1Predicted

68.8

GAIA Level 2Predicted

57.8

GAIA Level 3Predicted

34.4

GAIAPredicted

52.6 / 100

LegalBenchPredicted

91.9 / 100

LiveBench CodingPredicted

63.4 / 100

LiveBench Data AnalysisPredicted

38.4 / 100

LiveBench LanguagePredicted

64.3 / 100

LiveBench MathPredicted

55.1 / 100

LiveBench OverallPredicted

50.7 / 100

LiveBench ReasoningPredicted

52.7 / 100

LongBench v2 EasyPredicted

53.1

LongBench v2 HardPredicted

48.9

LongBench v2Predicted

44.1 / 100

MathVistaPredicted

67.0 / 100

MLE-benchPredicted

17.4 / 100

MMMUPredicted

74.8 / 100

MMTU Table UnderstandingPredicted

56.7 / 100

MT-BenchPredicted

8.0 / 10

NoLiMa (NIAH)Predicted

94.8 / 100

OCRBench v2Predicted

85.1 / 100

Open LLM AveragePredicted

36.7 / 100

Open LLM: BBHPredicted

65.1 / 100

Open LLM: GPQAPredicted

34.6 / 100

Open LLM: IFEvalPredicted

84.0 / 100

Open LLM: MATH Level 5Predicted

66.1 / 100

Open LLM: MMLU-PROPredicted

50.4 / 100

Open LLM: MUSRPredicted

45.0 / 100

RE-BenchPredicted

0.5

SimpleBenchPredicted

34.4 / 100

simpleqaPredicted

25.2

SWE-bench LitePredicted

30.7 / 100

SWE-bench VerifiedPredicted

49.0 / 100

tau-bench RetailPredicted

73.8 / 100

Vectara Factual ConsistencyPredicted

93.5 / 100

Vectara Hallucination RatePredicted

6.5 / 100

WebArenaPredicted

11.2 / 100

WeirdMLPredicted

38.6 / 100

WildBenchPredicted

50.2

BFCL (Berkeley Function Calling)bfcl

52.1

Chatbot Arena ELOchatbot_arena

259.0

Aider Polyglotepoch_ai

0.0

Arc Agi 2epoch_ai

0.0