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

TaxEval

A comprehensive tax analysis benchmark created in collaboration with financial and tax experts, featuring over 1,500 questions across validation and test sets. The evaluation focuses on both answer correctness and structured reasoning capabilities, covering six main question types: Application and Compliance, Comparative Analysis, Numerical Reasoning, Problem Solving and Critical Thinking, Semantic Analysis, and Updates and Current Affairs.

Source:

Model Performance

#1

GPT-5-mini

80.1%

#2

OpenAI-O3-high

79.0%

#3

OpenAI-O3-medium

79.0%

#4

Grok-3-Beta

78.8%

#5

OpenAI-O4-mini-high

78.8%

#6

Grok-3-Think

78.8%

#7

OpenAI-O4-mini-medium

78.8%

#8

OpenAI-O1-1217

78.6%

#9

Claude-3.7-Sonnet-Thinking

78.4%

#10

GPT-4.1

78.4%

#11

Qwen-3-Max-Preview

77.2%

#12

Claude-4.1-Opus-Thinking

77.2%

#13

Gemini-2.5-Pro-0325

76.7%

#14

DeepSeek-R1

76.7%

#15

Gemini-2.5-Pro-Thinking

76.7%

#16

Claude-3.7-Sonnet

75.9%

#17

Claude-4.0-Sonnet-Thinking

75.9%

#18

Claude-4.1-Opus

75.9%

#19

Claude-4.0-Opus

75.8%

#20

Grok-3-Mini-Beta

75.7%

#21

Gemini-2.5-Flash

75.4%

#22

DeepSeek-V3-0324

75.2%

#23

Qwen-3-Thinking

74.4%

#24

Gemini-2.5-Flash-Thinking

74.4%

#25

Qwen-3

74.4%

#26

Kimi-K2-Instruct

74.1%

#27

OpenAI-O3-mini-high

73.8%

#28

OpenAI-O3-mini-medium

73.8%

#29

Claude-3.5-Sonnet-1022

73.7%

#30

Claude-4.0-Sonnet

73.5%

#31

Mistral-Medium-3.1

73.4%

#32

Gemini-2.0-Flash-Thinking-0121

73.4%

#33

DeepSeek-V3

72.0%

#34

Gemini-2.0-Flash

70.3%

#35

Llama-4-Maverick-17B

69.3%

#36

Mistral-Large-2

67.7%

#37

Grok-4-Thinking

67.6%

#38

Grok-4

67.6%

#39

Cohere-Command-A

66.6%

#40

Llama-3.1-405B

66.3%

#41

GPT-4-mini

64.9%

#42

Gemini-1.5-Pro

64.9%

#43

Llama-3.3-70B

63.9%

#44

Claude-3.5-Haiku

63.0%