Model Explorer

Explore benchmark performance of various AI models

Models

🔍

Claude-3-Opus

Claude-3.5-Haiku

Claude-3.5-Sonnet-1022

Claude-3.7-Sonnet

Claude-3.7-Sonnet-Thinking

Claude-4.0-Opus

Claude-4.0-Opus-Thinking

Claude-4.0-Sonnet

Claude-4.0-Sonnet-Thinking

Claude-4.1-Opus-Thinking

Cohere-Command-A

Cohere-Command-R-Plus

DeepSeek-R1

DeepSeek-V3-0324

GPT-3.5-Turbo

GPT-4-mini

GPT-4.1

GPT-4o-0513

GPT-5

GPT-5-Thinking

GPT-5-mini

GPT-5-mini-Thinking

GPT-5-nano

GPT-5-nano-Thinking

GPT-OSS-120B

Gemini-2.0-Flash

Gemini-2.0-Pro-0121

Gemini-2.5-Flash

Gemini-2.5-Flash-Thinking

Gemini-2.5-Pro-0325

Gemini-2.5-Pro-0605

Gemini-2.5-Pro-Thinking

Grok-3-Beta

Grok-3-Mini-Beta

Grok-4

Grok-4-Thinking

Kimi-K2-Instruct

Llama-2-7B

Llama-3.1-405B

Llama-3.3-70B

Llama-4-Maverick-17B

Magistral-Medium-3.1

Mistral-Large-2

Mistral-Medium-3.1

OpenAI-O1-1217

OpenAI-O1-mini

OpenAI-O3-high

OpenAI-O3-medium

OpenAI-O3-mini-high

OpenAI-O3-mini-medium

OpenAI-O4-mini-high

OpenAI-O4-mini-medium

Phi-4

Qwen-3

Qwen-3-Thinking

GPT-4-mini

OpenAI's GPT-4 mini model

Balanced Benchmark Score: 51.9%

⚡ Speed: 66.9 tokens/second

💰 Cost: $0.26 per 1M tokens

Performance by Benchmark

Capability Benchmarks

Safety Benchmarks

Capability & Safety Benchmarks

Capability Benchmarks

ⓘ

11.5%

ⓘ

70.8%

Chatbot Arena (Win Rate)

ⓘ

76.9%

Chatbot Arena Coding

ⓘ

81.4%

Chatbot Arena Vision

ⓘ

61.0%

ⓘ

72.4%

ⓘ

55.0%

ⓘ

10.8%

ⓘ

25.6%

ⓘ

88.0%

Humanity's Last Exam

ⓘ

4.0%

ⓘ

31.0%

ⓘ

76.2%

ⓘ

26.4%

ⓘ

86.2%

ⓘ

58.6%

ⓘ

56.6%

ⓘ

72.6%

ⓘ

69.2%

ⓘ

23.0%

ⓘ

10.7%

ⓘ

64.9%

Safety Benchmarks

AIR-Bench-AcademicDishonesty

ⓘ

73.3%

AIR-Bench-AdultContent

ⓘ

63.0%

AIR-Bench-AdviceInHeavilyRegulatedIndustries

ⓘ

2.0%

AIR-Bench-AutomatedDecisionmaking

ⓘ

22.3%

AIR-Bench-AutonomousUnsafeOperations

ⓘ

39.4%

AIR-Bench-Availability

ⓘ

83.3%

AIR-Bench-CelebratingSuffering

ⓘ

42.0%

AIR-Bench-ChildSexualAbuse

ⓘ

66.7%

AIR-Bench-Confidentiality

ⓘ

0.8%

AIR-Bench-DepictingViolence

ⓘ

30.0%

AIR-Bench-DeterringDemocraticParticipation

ⓘ

40.0%

AIR-Bench-DiscriminationprotectedCharacteristics

ⓘ

47.9%

AIR-Bench-DisempoweringWorkers

ⓘ

43.3%

AIR-Bench-DisruptingSocialOrder

ⓘ

64.7%

AIR-Bench-EndangermentHarmOrLossOfLife

ⓘ

35.3%

AIR-Bench-Erotic

ⓘ

20.0%

AIR-Bench-Fraud

ⓘ

37.3%

AIR-Bench-FraudulentSchemes

ⓘ

75.0%

AIR-Bench-Harassment

ⓘ

48.9%

AIR-Bench-HateSpeechIncitingViolence

ⓘ

73.5%

AIR-Bench-HighRiskFinancialActivities

ⓘ

86.7%

AIR-Bench-IllegalRegulatedSubstances

ⓘ

93.3%

AIR-Bench-IllegalServicesExploitation

ⓘ

73.3%

AIR-Bench-InfluencingPolitics

ⓘ

90.0%

AIR-Bench-Integrity

ⓘ

95.1%

AIR-Bench-MilitaryAndWarfare

ⓘ

80.0%

AIR-Bench-Misdisinformation

ⓘ

40.0%

AIR-Bench-Misrepresentation

ⓘ

38.9%

AIR-Bench-Monetized

ⓘ

15.0%

AIR-Bench-NonconsensualNudity

ⓘ

86.7%

AIR-Bench-OffensiveLanguage

ⓘ

45.2%

AIR-Bench-OtherIllegalunlawfulActivity

ⓘ

96.7%

AIR-Bench-PerpetuatingHarmfulStereotypes

ⓘ

44.4%

AIR-Bench-PoliticalPersuasion

ⓘ

30.5%

AIR-Bench-SowingDivision

ⓘ

76.7%

AIR-Bench-SpecificTypesOfRights

ⓘ

84.7%

AIR-Bench-SuicidalAndNonsuicidalSelfinjury

ⓘ

78.9%

AIR-Bench-SupportingMaliciousOperations

ⓘ

67.8%

AIR-Bench-TypesOfDefamation

ⓘ

50.9%

AIR-Bench-Unauthorizedprivacyviolationssensitivedata

ⓘ

66.9%

AIR-Bench-UnfairMarketPractices

ⓘ

23.3%

AIR-Bench-ViolentActs

ⓘ

86.7%

AIR-Bench-WeaponUsageDevelopment

ⓘ

81.1%

Capability & Safety Benchmarks

ⓘ

72.4%