Skip to content

Anthropic · Chat

Claude Opus 4.5

Anthropic 🇺🇸ChatClaude familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (22 Feb 2027). Plans can change.

Newer version: Claude Opus 5.5. We compared release dates and version names in our catalogue.

From Neosantara's listing:
Claude 4.5 Opus is Anthropic's most powerful model, designed for highly complex tasks, deep reasoning, and creative endeavors with a massive context window.
llminfo IQ
134.0
Maker's price
$10.00 blended / 1M
Max context
1M
Listings
96

Evidence and sources

llminfo IQ 134.0, ranked among chat models. From 384 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 112.8, 95% interval 108–118. From 20 benchmark families across 13 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (46.0). Costs more per task than its benchmark results predict. From 45 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 33,371 output tokens per task at default effort.How the Yap score worksReleased 24 Nov 2025Maker HQ: US (according to Anthropic's own website)
All rankings: #35 in Hacker News discussions this week #208 on OpenRouter today #220 on OpenRouter this week #229 on OpenRouter this month #313 on NanoGPT recentlyAll rankings: #35 in Hacker News discussions this week #208 on OpenRouter today #220 on OpenRouter this week #229 on OpenRouter this month #313 on NanoGPT recentlySources: Anthropic API data, Heroku Managed Inference data, LiteLLM data, Models.dev data, Neosantara Inference data, llminfo researchPrimary data from Anthropic API from Heroku Managed Inference: primary mode from LiteLLM: deprecation date from Models.dev: weights availability from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningdocumentproprietarylong-contextpremium

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 22 Feb 2027, within the next 180 days.

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputComputer useWeb searchBatch API

Listings

 Anthropicclaude-opus-4.5Sources: Anthropic pricing page, GenAI Prices data, LiteLLM data, Models.dev data200K$5.00cache read $0.50batch $2.50$25.00cache write 5m $6.25cache write 1h $10.00batch $12.50
 OpenRouteranthropic/claude-opus-4.5:batch · batchSource: OpenRouter data docs200K$2.50cache read $0.25$12.50cache write 5m $3.125cache write 1h $5.00
 Vercelanthropic/claude-opus-4.5-batch · batchSource: Vercel AI Gateway data200K$2.50cache read $0.25$12.50
 Meganovaanthropic/claude-opus-4-5-20251101 · 20251101Source: MegaNova data200K$4.00$20.00
 Poeanthropic/claude-opus-4.5Source: Models.dev data197K$4.2929cache read $0.4293$21.465cache write $5.3662
 Jiekouclaude-opus-4-5-20251101 · 20251101Source: Models.dev data200K$4.75cache read $0.475$23.75cache write $5.9375
 Amazon Web Servicesanthropic.claude-opus-4-5-20251101-v1:0 · 20251101Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data200K$5.00cache read $0.50$25.00cache write 5m $6.25cache write 1h $10.00
 Microsoft Azureazure_ai/claude-opus-4-5Sources: LiteLLM data, Models.dev data200K$5.00cache read $0.50$25.00cache write 5m $6.25cache write 1h $10.00
 Googlevertex_ai/claude-opus-4-5Source: LiteLLM data200K$5.00cache read $0.50batch $2.50$25.00cache write 5m $6.25cache write 1h $10.00batch $12.50
 302aiclaude-opus-4-5-20251101 · 20251101Sources: 302.ai data, Models.dev data200K$5.00$25.00

10 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
launch-page footnote · basic fetch configuration
launch-page footnote · full context-management configuration
Qwen3-Embedding-8B index · tool-result clearing · no fetch · Sonnet 4.5 grader
Qwen3-Embedding-8B index · tool-result clearing + memory/context reset · Sonnet 4.5 grader
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
64K thinking · 200K context · avg@8
Anthropic internal · 64K thinking · 1M context · avg@4
GAIA4 results
Source: GAIA Leaderboard data · Jan 2026
Difficulty level
Difficulty not reported
MCP Atlas3 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
no extended thinking · 200K context · default sampling
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Open Agent Leaderboard6 related benchmarks · 30 results
SWE-bench
Source: Open Agent Leaderboard results data docs
By agent · task: swebench · route: openai/aws
AppWorld test_normal
Source: Open Agent Leaderboard results data docs
By agent · task: appworld_test_normal · subset: test_normal · route: openai/aws
BrowseCompPlus
Source: Open Agent Leaderboard results data docs
By agent · task: browsecompplus · route: openai/aws
Tau Bench 2 airline
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_airline · subset: airline · route: openai/aws
Tau Bench 2 retail
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_retail · subset: retail · route: openai/aws
Tau Bench 2 telecom
Source: Open Agent Leaderboard results data docs
By agent · task: tau2_telecom · subset: telecom · route: openai/aws
OpenHandsSource: OpenHands Index data
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
1080p · max 100 steps · pass@1 · avg@5 · 64K thinking · 200K context
Opus 4.6 System Card setting
SpreadSheetBench-v1full 912 tasks · custom bash/Python/LibreOffice harness · no extended thinking · 200K context · avg@5 · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-Bench Pro200K context · avg@5 · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Tau2 Retail15 related benchmarks · 20 results
Tau2 Retail
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Telecom
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
tau2-bench airline
Source: OpenRouter benchmark exports
24 Nov 2025 version · 90-day results
Across 5 providers lowest 75.1% median 75.3% highest 75.8%OpenRouter's automatic routing 75.6%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • Anthropic
  • OpenRouter's automatic routing
  • Claude Platform on AWS
  • Google
  • Amazon Bedrock
  • Azure
tau2-bench v1 airline pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 airline pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 airline pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
Show 9 more resultsHide 9 results
tau2-bench v1 airline pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 retail pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 retail pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 retail pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 retail pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 telecom pass^1
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 telecom pass^2
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 telecom pass^3
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
tau2-bench v1 telecom pass^4
Source: Sierra tau-bench Leaderboard data docs · May 2026
submission-claude-opus-4-5_sierra_2026-02-26, usersim-gpt-5.2, effort-high
Terminal-Bench3 related benchmarks · 6 results
Terminal-Bench
Source: Epoch AI Benchmarking Hub data
Setting not stated
2.0 · Terminus-2
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Harbor · Terminus-2 · 128K thinking budget · 1,335 trials
Harbor · Terminus-2 · 64K thinking budget · 2,225 trials
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Terminal-Bench 2.0
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
WebArena4 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Attempts · Computer Use API + browser tools · single policy · general prompts · official grader
pass@1 · Computer Use API + browser tools · single policy · general prompts · official grader · avg@5

Human preference

Arena ELO57 related benchmarks · 107 results
Source: LMArena data · Nov 2026
Arena ELO
Chinese
Creative Writing
Document
Document Style-Controlled
English
Show 97 more resultsHide 97 results
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Search Factuality
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Reasoning

ARC-AGI4 related benchmarks · 13 results
ARC-AGI
Source: Epoch AI Benchmarking Hub data
Setting not stated
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted · Verified
private validation · 64K thinking tokens
ARC-AGI-1
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
private validation · 64K thinking tokens
v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CL-bench5 related benchmarks · 15 results
Overall
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Domain Knowledge Reasoning
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Empirical Discovery & Simulation
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Procedural Task Execution
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Rule System Application
Reported by Tencent Hunyuan / Fudan NLP Group · via BenchBoard docs
By site model-mode label · benchmark-owner leaderboard run · 1899 tasks · GPT-5.1 judge · low reasoning effort · candidate API snapshot and exact candidate harness not specified on public leaderboard
Source: Epoch AI Benchmarking Hub data
Setting not stated
Humanity's Last Examreasoning only · without search/tools · decontaminated · Sonnet 4.5 grader · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Coding

CyberGympass@1 · 1,505 tasks · avg@5 · no thinking · 200K context · think tool · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-bench Verified9 related benchmarks · 13 results
SWE-bench Verified
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
200K context · avg@5
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench Multilingual
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
200K context · avg@5
Show 3 more resultsHide 3 results
ValsSource: Vals AI

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond11 results
Source: Epoch AI Benchmarking Hub data
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
64K thinking · interleaved scratchpads · 200K context · avg@5
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: OpenRouter benchmark exports · Oct 2026
24 Nov 2025 version · 90-day results
Across 5 providers lowest 85.8% median 86.4% highest 86.6%OpenRouter's automatic routing 86.3%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • Claude Platform on AWS
  • Anthropic
  • Azure
  • OpenRouter's automatic routing
  • Amazon Bedrock
  • Google
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
0-shot · image-crop tool · 32,768 reasoning-token budget
0-shot · no tools · no extended thinking

Math

AIME 202564K thinking · 200K context · avg@5 · contamination caveat · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
PutnamBench lean-wsolution solvedAxProverBase (Axiomatic AI), lean-wsolution, Opus 4.5 w/ 50 iterations, Claude Opus 4.5 in a minimal agent with tool calling, capped to 50 tool calls at 32k context. Harness open sourced. commit: 961af76, version: 4.29, problems: 1962 A5, 1962 A6, 1962 B1, 1962 B2, 1962 B3, 1963 A2, 1963 B1, 1963 B2, 1963 B5, 1963 B6, 1964 A2, 1964 A4, 1964 B1, 1964 B2, 1964 B3, 1964 B5, 1964 B6, 1965 A3, 1965 A4, 1965 A5, 1965 A6, 1965 B1, 1965 B2, 1965 B3, 1965 B5, 1966 A1, 1966 A3, 1966 A4, 1966 A5, 1966 A6, 1966 B2, 1966 B4, 1966 B6, 1967 A1, 1967 A3, 1967 B2, 1967 B4, 1968 A1, 1968 A2, 1968 A4, 1968 A5, 1968 B1, 1968 B2, 1968 B5, 1968 B6, 1969 A1, 1969 A5, 1969 A6, 1969 B1, 1969 B2, 1969 B3, 1969 B5, 1969 B6, 1970 A1, 1970 A2, 1970 A3, 1970 A4, 1970 B2, 1970 B3, 1970 B4, 1970 B5, 1971 A1, 1971 A2, 1971 A3, 1971 B1, 1971 B2, 1971 B3, 1971 B6, 1972 A1, 1972 A2, 1972 A5, 1972 B2, 1972 B3, 1972 B4, 1973 A3, 1973 A4, 1973 A6, 1973 B1, 1973 B2, 1973 B3, 1973 B4, 1974 A1, 1974 A3, 1974 A4, 1974 A6, 1974 B3, 1974 B4, 1974 B6, 1975 A1, 1975 A2, 1975 A3, 1975 A4, 1975 B1, 1975 B4, 1975 B6, 1976 A3, 1976 A4, 1976 A6, 1976 B2, 1976 B5, 1977 A1, 1977 A3, 1977 A5, 1977 B1, 1977 B5, 1978 A1, 1978 A4, 1978 A5, 1978 B4, 1978 B6, 1979 A1, 1979 A2, 1979 A3, 1979 A4, 1979 B2, 1979 B3, 1979 B6, 1980 A3, 1980 A5, 1980 B1, 1980 B3, 1980 B4, 1980 B5, 1981 A5, 1981 B1, 1981 B2, 1981 B3, 1981 B4, 1982 A2, 1982 A3, 1982 A5, 1982 B4, 1982 B5, 1983 A1, 1983 A3, 1983 A4, 1983 B4, 1984 A2, 1984 B1, 1984 B2, 1984 B3, 1985 A1, 1985 A3, 1985 A4, 1985 A6, 1985 B3, 1985 B6, 1986 A1, 1986 A2, 1986 A3, 1986 A6, 1986 B1, 1986 B2, 1986 B3, 1986 B4, 1986 B5, 1986 B6, 1987 A1, 1987 A2, 1987 B1, 1987 B2, 1987 B3, 1987 B4, 1987 B5, 1988 A1, 1988 A2, 1988 A3, 1988 A5, 1988 A6, 1988 B1, 1988 B2, 1988 B3, 1988 B4, 1988 B6, 1989 A2, 1989 A3, 1989 B2, 1989 B4, 1990 A1, 1990 A2, 1990 A5, 1990 A6, 1990 B1, 1990 B2, 1991 A2, 1991 A4, 1991 A5, 1991 A6, 1991 B1, 1991 B2, 1992 A1, 1992 A2, 1992 A5, 1992 B1, 1992 B2, 1993 A2, 1993 A4, 1993 B1, 1993 B3, 1993 B5, 1994 A1, 1994 A3, 1994 A4, 1994 B1, 1994 B3, 1994 B4, 1994 B5, 1994 B6, 1995 A1, 1995 A3, 1995 A4, 1995 B1, 1995 B3, 1995 B4, 1995 B6, 1996 A2, 1996 A3, 1996 A4, 1996 A5, 1996 B1, 1996 B2, 1996 B4, 1997 A4, 1997 B1, 1997 B2, 1997 B5, 1998 A3, 1998 A4, 1998 A5, 1998 B1, 1998 B2, 1998 B5, 1998 B6, 1999 A1, 1999 A2, 1999 A4, 1999 B4, 1999 B5, 2000 A1, 2000 A2, 2000 A5, 2000 A6, 2000 B1, 2000 B2, 2000 B4, 2000 B5, 2001 A1, 2001 B1, 2001 B2, 2001 B4, 2001 B6, 2002 A1, 2002 A2, 2002 A5, 2002 B5, 2003 A1, 2003 A2, 2003 A3, 2003 A4, 2003 A5, 2003 B1, 2003 B2, 2003 B3, 2003 B4, 2004 A1, 2004 A3, 2004 B1, 2004 B2, 2004 B4, 2005 A1, 2005 A4, 2005 A5, 2005 B1, 2005 B2, 2005 B3, 2006 A3, 2006 B2, 2006 B4, 2006 B5, 2006 B6, 2007 A1, 2007 A5, 2007 B1, 2007 B2, 2007 B5, 2008 A1, 2008 A5, 2008 B1, 2008 B3, 2008 B4, 2008 B5, 2009 A1, 2009 A3, 2009 B1, 2009 B2, 2009 B5, 2009 B6, 2010 A1, 2010 A2, 2010 A3, 2010 A4, 2010 B1, 2010 B5, 2010 B6, 2011 A2, 2011 A4, 2011 B1, 2011 B3, 2012 A1, 2012 A2, 2012 A3, 2012 B1, 2012 B3, 2012 B4, 2012 B5, 2013 A2, 2013 A3, 2013 B1, 2013 B2, 2013 B3, 2013 B4, 2013 B5, 2014 A2, 2014 A3, 2014 A4, 2014 A6, 2014 B2, 2015 A2, 2015 A3, 2015 A6, 2015 B1, 2016 A1, 2016 A2, 2016 A5, 2016 B1, 2017 A1, 2017 A2, 2017 A4, 2017 B1, 2017 B2, 2018 A1, 2018 A5, 2018 B2, 2018 B5, 2018 B6, 2019 A1, 2019 B3, 2019 B6, 2020 A2, 2020 A3, 2020 B1, 2020 B4, 2021 A1, 2021 A2, 2021 A5, 2022 A3, 2022 A4, 2022 B3, 2023 A1, 2023 A3, 2023 A6, 2023 B2, 2023 B3, 2024 A1, 2024 B1 · Source: PutnamBench

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs
MMMLU3 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
14 non-English languages · 64K thinking · 200K context · avg@10
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Vision

MMMU3 related benchmarks · 4 results
MMMU
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
validation · 64K thinking · interleaved scratchpads · 200K context · avg@5
(validation)
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Pro
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted

General

Factuality

OCR

Instruction following

Safety

PhareSource: Phare

Knowledge

Other

Horangi36 related benchmarks · 36 results
4: ALT_환각방지
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: haerae_bench_v1_rc
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: haerae_bench_v1_wo_rc
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: hrm8k
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: kmmlu
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: kmmlu_pro
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
Show 30 more resultsHide 30 results
4 subset: ko_aime2025
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_arc_agi
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_balt_700_semantic
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_balt_700_syntax
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_hallulens_nonexistent
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_hallulens_wikiqa
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_hle
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_moral
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: ko_truthful_qa
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: kobbq
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: korean_hate_speech
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4 subset: squad_kor_v1
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: ALT_유해성방지
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: ALT_윤리/도덕
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: ALT_제어성
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: ALT_편향성방지
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: FINAL_SCORE
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_구문해석
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_논리적추론
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_수학적추론
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_의미해석
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_일반적지식
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_전문적지식
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_정보검색
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_추상적추론
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_코딩능력
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_표현
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: GLP_함수호출
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: 가치정렬성능(ALT)_AVG
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
4: 범용언어성능(GLP)_AVG
Source: Horangi Korean Leaderboard 4 data docs
claude-opus-4-5-20251101: high-effort
Nejumi 428 related benchmarks · 56 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
Show 44 more resultsHide 44 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_表現
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-4.5-20251125: no-thinking
anthropic/claude-opus-4.5-20251125: extended-thinking
SurveyReview v1.012 related benchmarks · 12 results
Structure · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Comprehensiveness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Criticalness · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Four dimensions · Average MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Show 6 more resultsHide 6 results
Four dimensions · Average MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Human-aligned Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Overall · Reason Quality Score
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MAE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Readability · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Structure · MSE
Reported by SurveyReview authors / Z.ai · via BenchBoard docs
SurveyReview v1.0 published leaderboard · text survey-paper evaluation · exact candidate snapshot, reasoning effort, prompt, run count, and harness are not specified in the summary table
Vals7 related benchmarks · 11 results
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Setting not stated
Source: Vals AI
Setting not stated
CaseLaw v2
Source: Vals AI
CorpFin v2
Source: Vals AI
LegalBench
Source: Vals AI
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Setting not stated
Source: Vals AI
Setting not stated
MortgageTax
Source: Vals AI
Show 1 more resultHide 1 result
TaxEval v2
Source: Vals AI
τ²-bench3 related benchmarks · 7 results
Telecom
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Opus 4.1 user simulator · prompt addendum
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted
Airline
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
original task set
Anthropic-corrected task setup and grading · fixes submitted to benchmark authors
Retail
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Opus 4.1 user simulator · prompt addendum
Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · ChemBench leaderboard, Jablonka group / lamalab-org. Public verified numeric result summaries; results licence not separately stated. · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · CyBench — cite Zhang et al. 2025 · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · Steel.dev Agent Leaderboards, MIT (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · HAL (Princeton) — cite the HAL paper · HalluHard: Fan, Delsad, Flammarion and Andriushchenko (EPFL), arXiv:2602.01031 · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Open Agent Leaderboard results (Exgentic), CDLA-Permissive-2.0; agreement text at https://cdla.dev/permissive-2-0/. Fractions shown as percentages. (licence) · OpenHands Index (All Hands AI), Apache-2.0 (licence) · Phare (Giskard), CC BY 4.0 (licence) · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SWE-fficiency (swefficiency.com) leaderboard materials, CC BY 4.0; Human Expert reference row omitted (licence) · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Vectara Hallucination Leaderboard, Apache-2.0 (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Around the web

Also known as: anthropic-claude-opus-4.5, anthropic.claude-opus-4-5-20251101-v1:0, anthropic/claude-opus-4-5, anthropic/claude-opus-4-5-20251101, anthropic/claude-opus-4.5, anthropic/claude-opus-4.5-batch, anthropic/claude-opus-4.5:batch, anthropic/claude-opus-4.5:thinking, aws-bedrock/claude-opus-4-5-20251101, azure_ai/claude-opus-4-5, bedrock/claude-opus-4-5, bedrock/claude-opus-4-5@eu-central-1, bedrock/claude-opus-4-5@eu-north-1, bedrock/claude-opus-4-5@eu-west-1, bedrock/claude-opus-4-5@eu-west-3, bedrock/claude-opus-4-5@us-east-1, bedrock/claude-opus-4-5@us-east-2, bedrock/claude-opus-4-5@us-west-2, claude opus 4.5, claude-4.5-opus, claude-opus-4-5, claude-opus-4-5-20250514, claude-opus-4-5-20251101, claude-opus-4-5-20251101-thinking, claude-opus-4-5-think, claude-opus-4-5@20251101, claude-opus-4-5@eu, claude-opus-4.5-20251101, claude-opus-4.5-high-32k-20251101, claude-opus-4.5-search, claude-opus4-5, cometapi-opus-4-5-20251101, cometapi-opus-4-5-20251101-thinking, databricks-claude-opus-4-5, databricks/databricks-claude-opus-4-5, eu.anthropic.claude-opus-4-5-20251101-v1:0, global.anthropic.claude-opus-4-5-20251101-v1:0, global.anthropic.claude-opus-4-5-v1:0, gmi/anthropic/claude-opus-4.5, perplexity/anthropic/claude-opus-4-5, regional.anthropic.claude-opus-4-5-v1:0, snowflake/claude-opus-4-5, us.anthropic.claude-opus-4-5-20251101-v1:0, vercel_ai_gateway/anthropic/claude-opus-4.5, vertex-anthropic/claude-opus-4-5-20251101, vertex/claude-opus-4-5, vertex/claude-opus-4-5@europe-west1, vertex/claude-opus-4-5@us-east5, vertex_ai/claude-opus-4-5, vertex_ai/claude-opus-4-5@20251101

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works