Benchmark Explorer

Explore how models perform on various benchmarks

Benchmarks

🔍

Capability Benchmarks

AA-LCR

AIME

Blended Price (USD/1M Tokens)

CaseLaw

Chatbot Arena (Win Rate)

Chatbot Arena Coding

Chatbot Arena Vision

ContractLaw

CorpFin

FinanceAgent

GPQA

HumanEval

Humanity's Last Exam

IFBench

IOI

LegalBench

LiveBench (Agentic Coding)

LiveBench (Average)

LiveBench (Coding)

LiveBench (Data Analysis)

LiveBench (Instruction Following)

LiveBench (Language)

LiveBench (Math)

LiveBench (Reasoning)

LiveCodeBench

MGSM

MMLU Pro

MMMU

Math500

Median Tokens/s

MortgageTax

SWE-bench

SciCode

SimpleBench

TaxEval

Terminal-Bench Hard

τ²-Bench Telecom

Safety Benchmarks

AIR-Bench-AcademicDishonesty

AIR-Bench-AdultContent

AIR-Bench-AdviceInHeavilyRegulatedIndustries

AIR-Bench-AutomatedDecisionmaking

AIR-Bench-AutonomousUnsafeOperations

AIR-Bench-Availability

AIR-Bench-CelebratingSuffering

AIR-Bench-ChildSexualAbuse

AIR-Bench-Confidentiality

AIR-Bench-DepictingViolence

AIR-Bench-DeterringDemocraticParticipation

AIR-Bench-DiscriminationprotectedCharacteristics

AIR-Bench-DisempoweringWorkers

AIR-Bench-DisruptingSocialOrder

AIR-Bench-EndangermentHarmOrLossOfLife

AIR-Bench-Erotic

AIR-Bench-Fraud

AIR-Bench-FraudulentSchemes

AIR-Bench-Harassment

AIR-Bench-HateSpeechIncitingViolence

AIR-Bench-HighRiskFinancialActivities

AIR-Bench-IllegalRegulatedSubstances

AIR-Bench-IllegalServicesExploitation

AIR-Bench-InfluencingPolitics

AIR-Bench-Integrity

AIR-Bench-MilitaryAndWarfare

AIR-Bench-Misdisinformation

AIR-Bench-Misrepresentation

AIR-Bench-Monetized

AIR-Bench-NonconsensualNudity

AIR-Bench-OffensiveLanguage

AIR-Bench-OtherIllegalunlawfulActivity

AIR-Bench-PerpetuatingHarmfulStereotypes

AIR-Bench-PoliticalPersuasion

AIR-Bench-SowingDivision

AIR-Bench-SpecificTypesOfRights

AIR-Bench-SuicidalAndNonsuicidalSelfinjury

AIR-Bench-SupportingMaliciousOperations

AIR-Bench-TypesOfDefamation

AIR-Bench-Unauthorizedprivacyviolationssensitivedata

AIR-Bench-UnfairMarketPractices

AIR-Bench-ViolentActs

AIR-Bench-WeaponUsageDevelopment

Capability & Safety Benchmarks

MedQA

Chatbot Arena Coding

Evaluates the model's coding abilities through head-to-head comparisons in the Chatbot Arena platform, where human judges assess code quality, correctness, and implementation approach.

Source:

Model Performance

#1

Gemini-2.5-Pro-Thinking

95.4%

#2

Gemini-2.5-Pro-0325

95.4%

#3

Gemini-2.5-Pro-0605

95.4%

#4

Qwen-3-Max-Preview

95.1%

#5

GPT-5

94.6%

#6

GPT-5-Thinking

94.6%

#7

Grok-4

91.9%

#8

Grok-4-Thinking

91.9%

#9

Qwen-3

91.7%

#10

Qwen-3-Thinking

91.7%

#11

OpenAI-O3-medium

91.6%

#12

Grok-3-Beta

91.3%

#13

Claude-4.0-Opus-Thinking

90.6%

#14

Gemini-2.5-Flash

88.6%

#15

GPT-5-mini-Thinking

88.4%

#16

Claude-4.0-Sonnet-Thinking

87.4%

#17

Kimi-K2-Instruct

86.6%

#18

Claude-4.0-Opus

86.4%

#19

GPT-4.1

85.1%

#20

Gemini-2.0-Pro-0121

85.1%

#21

DeepSeek-V3

84.4%

#22

DeepSeek-V3-0324

84.4%

#23

Mistral-Medium-3.1

83.9%

#24

OpenAI-O4-mini-high

83.6%

#25

OpenAI-O4-mini-medium

83.6%

#26

Claude-4.0-Sonnet

83.4%

#27

Gemini-2.0-Flash-Thinking

83.3%

#28

Gemini-2.0-Flash-Thinking-0121

83.3%

#29

DeepSeek-R1

83.1%

#30

OpenAI-O3-mini-high

82.9%

#31

Grok-3-Mini-Beta

82.9%

#32

OpenAI-O1-1217

82.6%

#33

Gemini-2.0-Flash

81.6%

#34

GPT-4-mini

81.4%

#35

OpenAI-O1-mini

80.9%

#36

GPT-5-nano-Thinking

80.4%

#37

OpenAI-O3-mini-medium

80.1%

#38

Llama-3.3-70B

79.9%

#39

Claude-3.7-Sonnet-Thinking

79.3%

#40

Llama-3.1-405B

77.9%

#41

Claude-3.7-Sonnet

77.3%

#42

Claude-3.5-Sonnet-1022

77.1%

#43

Cohere-Command-A

76.6%

#44

Gemini-1.5-Pro

73.0%

#45

GPT-4o-0513

72.4%

#46

Claude-3-Opus

67.0%

#47

Claude-3-Sonnet

61.7%

#48

Cohere-Command-R-Plus

57.1%

#49

GPT-3.5-Turbo

52.0%

#50

Llama-2-13B

39.6%