LLMfamily
Claude
Anthropic's proprietary model family, including the Opus, Sonnet, Haiku, Fable and Mythos tiers; no open-weight relatives.
Levelfamily
ClassLLM
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessproprietary
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reportedmaintainer-runindependent
AI2Dmultimodal
88.1
050100
Score in %. Higher is better.
Claude 3 model card, Table 1 and vision table
ARC-AGI-2knowledge and reasoning
Arena Agenthuman preference arena
14.33
050100
Score in %. Higher is better.
rank 1, Arena Agent overall
Arena Text leaderboardhuman preference arena
1,476 ±9
1,2001,4001,600
Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.
rank 32, Arena Text overall
Arena Vision leaderboardhuman preference arena
1,308 ±7
rank 1 of 165, Arena Vision overall, style control default, 165 models
1,299 ±6
rank 3 of 165, Arena Vision overall, style control default, 165 models
1,293 ±13
rank 11 of 165, Arena Vision overall, style control default, 165 models
1,286 ±10
1,2701,2901,310
Score in Elo; the axis starts at 1,270, as Elo has no zero. Higher is better.
rank 17 of 165, Arena Vision overall, style control default, 165 models
Artificial Analysis Intelligence Index v4.3.2composite index
58
rank 1 of 205, AA leaderboard, 205 current models
43
090180
Score in index. Higher is better.
AA leaderboard, 205 current models
benchlm.ai frontier compositecomposite index
CursorBenchcoding
Epoch Capabilities Index (ECI)composite index
Claude Opus 5.5maintainer-run
166.82 CI 163.54 to 170.99
090180
Score in index. Higher is better.
rank 1, Epoch AI Benchmarking Hub
FrontierCode v1.1coding
GDPval-AA v2.1agents and tool use
Claude Opus 5vendor-reported
1,708
1,6001,7501,900
Score in Elo; the axis starts at 1,600, as Elo has no zero. Higher is better.
GPQA Diamondknowledge and reasoning
40.4
050100
Score in %. Higher is better.
Claude 3 model card, Table 1 and vision table
GSM8Kmath
92.3
050100
Score in %. Higher is better.
Claude 3 model card, Table 1 and vision table
HumanEvalcoding
73
050100
Score in %. Higher is better.
Claude 3 model card, Table 1 and vision table
Humanity's Last Examknowledge and reasoning
Humanity's Last Exam (HLE)knowledge and reasoning
65
050100
Score in %. Higher is better.
rank 1, BenchLM aggregator, top score
IOIcoding
LiveCodeBenchcoding
90.5
050100
Score in %. Higher is better.
rank 1, Vals.ai run shown on BenchLM
MGSMmath
90.7
050100
Score in %. Higher is better.
Claude 3 model card, Table 1 and vision table
MMMUmultimodal
73.7
050100
Score in %. Higher is better.
Anthropic announcement
Multilingual MMLUknowledge and reasoning
87.4
050100
Score in %. Higher is better.
Anthropic announcement
OSWorld 2.0agents and tool use
OSWorldagents and tool use
ProgramBenchcoding
SWE-bench Procoding
SWE-bench Verifiedcoding
96
rank 1, BenchLM aggregator, top score
Claude Opus 4.1No extended thinking; bash and string-replace file editor scaffold; full 500 problemsvendor-reported
74.5
Anthropic announcement
72.5
Anthropic announcement
tau-benchagents and tool use
Terminal-Bench 2.1agents and tool use
85.02
050100
Score in %. Higher is better.
Terminal-Bench 2.0agents and tool use
Terminal-Bench 4.0agents and tool use
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
9 members have no release date in the notes, so they are not on this timeline.
Claude Haiku 5.5 belongs to this familymultimodal LLM7 Oct 2026Claude Sonnet 5.5 belongs to this familymultimodal LLM28 Sep 2026Claude Opus 5.5 belongs to this familymultimodal LLM22 Sep 2026Claude Fable 5.1 belongs to this familymultimodal LLM1 Sep 2026Claude Fable 5 belongs to this familyLLM9 Jun 2026Claude Opus 4.6 belongs to this familyLLMFeb 2026Claude Opus 4.1 belongs to this familyLLM5 Aug 2025Claude Opus 4 belongs to this familyLLM22 May 2025Claude 3.5 Sonnet (Oct '24) belongs to this familymultimodal LLM22 Oct 2024Claude 3 Haiku belongs to this familymultimodal LLM13 Mar 2024Claude 3 Opus belongs to this familymultimodal LLM4 Mar 2024Claude 3 Sonnet belongs to this familymultimodal LLM4 Mar 2024Claude 3.7 Sonnet belongs to this familyLLMClaude Haiku 4.5 belongs to this familyLLMClaude Mythos 5 belongs to this familyLLMClaude Mythos 5.1 belongs to this familyLLMClaude Opus 4.7 belongs to this familyLLMClaude Opus 4.8 belongs to this familyLLMClaude Opus 5 belongs to this familyLLMClaude Sonnet 4.6 belongs to this familyLLMClaude Sonnet 5 belongs to this familyLLMWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- not in the notes
- Output
- not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- proprietary
- Licence
- not in the notes sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAnthropicfrontier lab, USA
Anthropicfrontier lab, USAModelClaudeAnthropic, LLM
ClaudeAnthropic, LLMR&D TopicsFrontier Pretraining Scaling
Use CasesIndustrial Copilots and Maintenance AssistantsIndustrialClinical LLM (Frontier Proprietary)HealthcarePharma Documents, Regulatory and Life-Science R&DHealthcareAmbient Clinical ScribingHealthcare+2 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.Models 21
Claude Mythos 5Anthropic, LLMFamilyClaude 3.5 Sonnet (Oct '24)Anthropic, multimodal LLMFamilyClaude Opus 4Anthropic, LLMFamilyClaude Opus 4.1Anthropic, LLMFamilyClaude 3.7 SonnetAnthropic, LLMFamilyClaude Fable 5Anthropic, LLMFamilyClaude Fable 5.1Anthropic, multimodal LLMFamilyClaude Mythos 5.1Anthropic, LLMFamilyClaude Opus 4.7Anthropic, LLMFamilyClaude Opus 4.8Anthropic, LLMFamilyClaude Opus 5Anthropic, LLMFamilyClaude Haiku 4.5Anthropic, LLMFamily+9
Claude Haiku 5.5Anthropic, multimodal LLMFamilyClaude Opus 4.6Anthropic, LLMFamilyClaude Opus 5.5Anthropic, multimodal LLMFamilyClaude Sonnet 5Anthropic, LLMFamilyClaude Sonnet 5.5Anthropic, multimodal LLMFamilyClaude 3 HaikuAnthropic, multimodal LLMFamilyClaude 3 OpusAnthropic, multimodal LLMFamilyClaude 3 SonnetAnthropic, multimodal LLMFamilyClaude Sonnet 4.6Anthropic, LLMFamilyOrganisations 1
Sources
- Newsroom anthropic.com https://www.anthropic.com/news
- Models overview platform.claude.com https://platform.claude.com/docs/en/models/overview
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Claude", https://aurion.semai.id/models/anthropic-claude/, records of October 2026.