Skip to content

Anthropic · Chat

Claude Opus 5

Anthropic 🇺🇸ChatClaude familyOne of its sources says the weights aren't publicly available.The maker currently lists 8 Jul 2027 as the deprecation date. Plans can change.

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

From Netmind's listing:
Claude Opus 5 is the most capable Opus-tier model from Anthropic, built for complex agentic coding and enterprise work. It delivers frontier reasoning and long-horizon autonomy, with a 1M token context window, up to 128K output tokens, adaptive thinking with selectable reasoning effort, multimodal input, native tool use, and prompt caching.
llminfo IQ
143.9
Maker's price
$10.00 blended / 1M
Max context
1M
Listings
114

Evidence and sources

llminfo IQ 143.9, ranked among chat models. From 389 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 133.8, 95% interval 128–140. From 28 benchmark families across 12 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 computedGood value (64.6). Cheaper per task than its benchmark results predict. From 57 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 resultsChatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. By effort: default 51 · low 40 · medium 46 · high 54 · max 61.Median 91,672 output tokens per task at max effort.How the Yap score worksReleased 24 Jul 2026Maker HQ: US (according to Anthropic's own website)
All rankings: #4 in YouTube mentions this week #23 in Wikipedia pageviews this week #34 in Bluesky discussions this week #71 on OpenRouter this month #80 on OpenRouter this week #103 on OpenRouter today #191 on NanoGPT recentlyAll rankings: #4 in YouTube mentions this week #23 in Wikipedia pageviews this week #34 in Bluesky discussions this week #71 on OpenRouter this month #80 on OpenRouter this week #103 on OpenRouter today #191 on NanoGPT recentlySources: Anthropic API data, LiteLLM data, Models.dev data, AI/ML API data, NetMind.AI, llminfo researchPrimary data from Anthropic API from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from NetMind.AI: description from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningdocumentproprietarycodingagenticlong-context

Advantages and trade-offs

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

Advantages

Trade-offs

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 10 maker's prices.

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-5Sources: Anthropic API data, GenAI Prices data, LiteLLM data, Models.dev data1M$5.00cache read $0.50batch $2.50$25.00cache write 5m $6.25cache write 1h $10.00batch $12.50
 Jzstokenclaude-opus-5Source: Models.dev data1M$1.17cache read $0.1168$5.84cache write $1.46
 Teapot Routerclaude-opus-5Source: Models.dev data1M$1.75$8.75
 Xxapiclaude-opus-5Source: Models.dev data1M$1.923cache read $0.1923$9.615cache write $2.404
 Nous Portalanthropic/claude-opus-5:batch · batchSource: Nous Portal Inference Gateway data1M$2.50cache read $0.25$12.50cache write $3.125
 OpenRouterInference by Anthropicanthropic/claude-opus-5:batch · batchSource: OpenRouter data docs1M$2.50cache read $0.25$12.50cache write 5m $3.125cache write 1h $5.00
 Vercelanthropic/claude-opus-5-batch · batchSource: Vercel AI Gateway data1M$2.50cache read $0.25$12.50
 Outerlabsclaude-opus-5Source: Models.dev data1M$3.00cache read $0.30$15.00cache write $3.75
 Korouterclaude-opus-5Source: Models.dev data1M$3.25cache read $0.325$16.25cache write $4.06
 Kunavoclaude-opus-5Source: Models.dev data1M$3.50cache read $0.35$17.50cache write $4.375

13 listings without a price are hidden.

Benchmarks

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

Agentic

Agentic IF Indexmax · Meta internal composite · agentic instruction following · Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort
OpenAI launch table · highest published effort
BrowseComp15 results
Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · in-house search/visit/python harness · 500 steps · discard-all context strategy
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Show 11 more resultsHide 11 results
Source: OpenRouter benchmark exports
exa search · OpenRouter's web plugin · medium effort
exa search · OpenRouter's search tool · up to 1 turn · high effort
exa search · OpenRouter's search tool · up to 25 turns · high effort
exa search · OpenRouter's search tool · up to 5 turns · high effort
parallel search · OpenRouter's search tool · up to 1 turn · high effort
parallel search · OpenRouter's search tool · up to 25 turns · high effort
parallel search · OpenRouter's search tool · up to 5 turns · high effort
perplexity search · OpenRouter's web plugin · medium effort
perplexity search · OpenRouter's search tool · up to 1 turn · high effort
perplexity search · OpenRouter's search tool · up to 25 turns · high effort
perplexity search · OpenRouter's search tool · up to 5 turns · high effort
DeepResearch Bench IIAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · identical search tools · four-hour task limit · GPT-5.5 judge · three independent scoring passes · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GDPval · Atria paper EloAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 220 tasks · AgentCompass / OpenHands · four-hour limit · 250 steps · GLM-5.3 rubric judge · pairwise Elo · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
GDPval-AA v27 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Anthropic Fable/Mythos 5.1 launch table
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section · Artificial Analysis · max effort
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · Artificial Analysis Stirrup · 220 tasks · shell + web browsing · human baseline 1000
Show 1 more resultHide 1 result
JobBench2 results
Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · official OpenCode harness · main split / 65 tasks · 7,200-second limit · two attempts · Grok-4.3 judge · mean task score
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · 65 tasks · official evaluation code · OpenCode · file-aware rubric grader · mean rubric score
OSWorld5 related benchmarks · 22 results
OSWorld 2
Source: Epoch AI Benchmarking Hub data
medium / batch tool
Source: Steel.dev Agent Leaderboards data · Jul 2026
Setting not stated
2.0 · Binary
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · OSWorld 2.0 v08.08 · 108 tasks · common internal framework · binary completion
2.0 · Partial
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
2026-08 task set · partial
Opus 5.5 System Card capability section · 2026-09-10 task/assets · updated harness · max · 5 runs
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · partial
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · OSWorld 2.0 v08.08 · 108 tasks · common internal framework · partial reward
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · OSWorld 2.0 offline v2026.08.08
v2026.08.08 · offline set · partial score
2.0 · Strict
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
2026-08 task set · strict
Opus 5.5 System Card capability section · 2026-09-10 task/assets · updated harness · max · 5 runs
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · strict
OSWorld 2.0
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 100 EHR tasks · max · five attempts/task
Source: Clinical Benchmarks data docs · Reported by the model's developer. The source relaying it did not verify it. claim · Sep 2026
Setting not stated
SWE-Atlas · Codebase Q&Amax · provider model card · public QnA split · mean pass@1 · Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-Bench Pro4 results
Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · OpenHands v1.23.0 · 4.5-hour limit · 250 interaction steps · network disabled and Git history removed
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Source: OpenRouter benchmark exports · Oct 2026
23 Jul 2026 version · 90-day results
Across 5 providers lowest 75.9% median 77% highest 77.3%OpenRouter's automatic routing 77.9%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Amazon Bedrock
  • Google
  • Azure
  • Claude Platform on AWS
  • Anthropic
Terminal-Bench4 related benchmarks · 25 results
Terminal-Bench 2.1
Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · four-run mean · 12× timeout multiplier capped at 12 hours · 500 turns · Claude Code v2.1.224 except GPT models use Terminus 2 · Opus 4.8 fallback on a subset of tasks
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · 89 tasks · native coding harness · isolated cloud sandbox · pass@1
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Science 0.1
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Code harness
Opus 5.5 System Card capability section · Claude Code --bare · max · 12 trials/task
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Terminal-Bench 3.0
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek Harness / max effort
DeepSeek V4.1 launch chart · settings unspecified
Terminal-Bench 4.0
Reported by Terminal-Bench / Stanford / Harbor / Laude Institute · via BenchBoard docs
Reasoning effort · Terminal-Bench 4.0 official leaderboard · Claude Code
Source: LLM Stats data
Setting not stated
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Anthropic Fable/Mythos 5.1 launch table
Opus 5.5 System Card capability section · Claude Code --bare · max
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek Harness / max effort
DeepSeek V4.1 launch chart · settings unspecified
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Non-code · max effort
OpenAI launch table

Human preference

Arena ELO66 related benchmarks · 116 results
Source: LMArena data · Nov 2026
BenchmarkHighMax
Arena ELO
Chinese
Creative Writing
DocumentNot measured
Show 62 more benchmarksHide 62 benchmarks
BenchmarkHighMax
Document Style-ControlledNot measured
English
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 FactualityNot measured
Search Style-ControlledNot measured
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 - GermanNot measured
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
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 - JapaneseNot measured
Text Factuality - KoreanNot measured
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
VisionNot measured
Vision - ChineseNot measured
Vision - Creative Writing VisionNot measured
Vision - DiagramNot measured
Vision - EnglishNot measured
Vision - HomeworkNot measured
Vision - HumorNot measured
Vision Style-ControlledNot measured
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Reasoning

ARC-AGI4 related benchmarks · 11 results
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
ARC-AGI-1
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
ARC-AGI-3
Reported by OpenAI, Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
AutomationBench13 results
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Anthropic Fable/Mythos 5.1 launch table
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card · adaptive thinking · max effort unless stated · v1.0.6 leaderboard · max effort
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort
Show 3 more resultsHide 3 results
OpenAI launch table
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · public v3 · 600 tasks · benchmark automation tools · pass@1
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
AutomationBench v1.0.6Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · v1.0.6 with null-type fix from PR #13 · candidate harness and task count unstated · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
BabyVisionDeepSeek V4.1 launch chart · settings unspecified · with tools · Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Anthropic Opus 5 launch table · adaptive thinking · max effort unless noted
Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Difficult · 17 tasks
Opus 5.5 System Card · adaptive thinking · max effort unless stated · Human Solvable · 73 tasks
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Chartography2 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · with tools
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5.5 System Card capability section · no tools
DeepSearchQA10 results
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · 900 questions · common browser search/open/find harness · semantic answer matching
Show 9 more resultsHide 9 results
Source: OpenRouter benchmark exports · Aug 2026
exa search · OpenRouter's search tool · up to 1 turn · high effort
exa search · OpenRouter's search tool · up to 25 turns · high effort
exa search · OpenRouter's search tool · up to 5 turns · high effort
parallel search · OpenRouter's search tool · up to 1 turn · high effort
parallel search · OpenRouter's search tool · up to 25 turns · high effort
parallel search · OpenRouter's search tool · up to 5 turns · high effort
perplexity search · OpenRouter's search tool · up to 1 turn · high effort
perplexity search · OpenRouter's search tool · up to 25 turns · high effort
perplexity search · OpenRouter's search tool · up to 5 turns · high effort
HLE9 results
Show 9 more resultsHide 9 results
Source: OpenRouter benchmark exports · Aug 2026
exa search · OpenRouter's search tool · up to 1 turn · high effort
exa search · OpenRouter's search tool · up to 25 turns · high effort
exa search · OpenRouter's search tool · up to 5 turns · high effort
parallel search · OpenRouter's search tool · up to 1 turn · high effort
parallel search · OpenRouter's search tool · up to 25 turns · high effort
parallel search · OpenRouter's search tool · up to 5 turns · high effort
perplexity search · OpenRouter's search tool · up to 1 turn · high effort
perplexity search · OpenRouter's search tool · up to 25 turns · high effort
perplexity search · OpenRouter's search tool · up to 5 turns · high effort
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · full set
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · no tools
Opus 5.5 System Card capability section · no tools
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · no tools
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted · with tools
Opus 5.5 System Card capability section · with tools
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · with tools
Reported by OpenAI, Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MILUOpus 5.5 System Card · adaptive thinking · max effort unless stated · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OfficeQAOpus 5.5 System Card capability section · same Opus 5.5 card setup · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OfficeQA ProOpus 5.5 System Card capability section · same Opus 5.5 card setup · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Toolathlon Verifiedinternal pinned harness · adaptive thinking · max · 108 tasks · 3 trials · Pass@1 · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
WideSearch9 results
Show 9 more resultsHide 9 results
Source: OpenRouter benchmark exports · Aug 2026
exa search · OpenRouter's search tool · up to 1 turn · high effort
exa search · OpenRouter's search tool · up to 25 turns · high effort
exa search · OpenRouter's search tool · up to 5 turns · high effort
parallel search · OpenRouter's search tool · up to 1 turn · high effort
parallel search · OpenRouter's search tool · up to 25 turns · high effort
parallel search · OpenRouter's search tool · up to 5 turns · high effort
perplexity search · OpenRouter's search tool · up to 1 turn · high effort
perplexity search · OpenRouter's search tool · up to 25 turns · high effort
perplexity search · OpenRouter's search tool · up to 5 turns · high effort

Coding

BenchCADOpenAI launch table · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Cursor · via BenchBoard docs
Reasoning effort · Cursor production agent
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Cursor production agent · max effort
ExploitBenchOpenAI launch table · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Anthropic self-run · xhigh
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
FrontierCode4 related benchmarks · 14 results
FrontierCode
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
1.1 Extended
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5.5 System Card capability section · best reported effort
1.1 Main
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section · best reported effort
FrontierCode 1.1
Source: FrontierCode data
Source: LLM Stats data
Setting not stated
SkillsBenchLing-3.1-flash official chart · SkillsBench · version, task count, harness, reasoning setting and run count not stated · Reported by Ant inclusionAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-bench3 related benchmarks · 7 results
Multilingual
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Multimodal
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
ValsSource: Vals AI

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs
NepNewsBench v2 draft40 related benchmarks · 40 results
entity F1 (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
core fact recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
core fact recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
core fact recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
coverage precision proxy (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
Show 34 more resultsHide 34 results
coverage precision proxy (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
coverage precision proxy (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
effective score (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
effective score (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
effective score (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
English prose quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
English prose quality (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
English prose quality (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity F1 (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity F1 (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity precision (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity precision (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity precision (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
entity recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
Nepali prose quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
Nepali prose quality (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
Nepali prose quality (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
supporting fact recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
supporting fact recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
supporting fact recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
valid-answer quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
valid-answer quality (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off
valid-answer quality (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Anthropic via openrouter, reasoning off

General

Science

GPQA Diamond12 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Pass@1 / max effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
Source: OpenRouter benchmark exports
23 Jul 2026 version · 90-day results
Across 5 providers lowest 88.3% median 89.3% highest 90%OpenRouter's automatic routing 88.1%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • Azure
  • Anthropic
  • Google
  • Amazon Bedrock
  • Claude Platform on AWS
  • OpenRouter's automatic routing
ValsSource: Vals AI

Math

ArxivMathOpus 5.5 System Card capability section · August 2026 · no tools · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ArxivMath · With toolsOpus 5.5 System Card capability section · August 2026 · code sandbox · no internet · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
PutnamBench lean-wsolution solvedForall (Astrio), lean-wsolution, actor-side cost/problem; Reported 672/672 Lean wsolution proofs using Claude Opus 5 at xhigh reasoning; 662 accepted in round 1 and 10 in round 2. Actor-side total; reviewer and infrastructure costs not reported. Lean v4.33.1; statements based on PutnamBench commit f423c17. Evaluated harness is not public and the model is proprietary; proofs and submission evidence were shared privately. · Source: PutnamBench

Vision

LVBenchGemini为agentic;跨模型设置见原卡 · Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Long context

Instruction following

Knowledge

Global MMLU (GMMLU)Opus 5.5 System Card · adaptive thinking · max effort unless stated · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Factuality

OCR

Safety

Speech

Other

Artificial Analysis8 related benchmarks · 12 results
Briefcase
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
Opus 5.5 System Card capability section · v1.1 · Artificial Analysis · max effort
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Intelligence Index
Source: OpenRouter data docs
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Artificial Analysis Intelligence Index v4.1.1
Show 2 more resultsHide 2 results
BlenderWorld15 related benchmarks · 15 results
Art & Animation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 30 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Architecture & Interiors
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 72 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Characters & Animals
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 25 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Fully satisfied rubric
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Image/video-input overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 145 image or video reference tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Nature & Landscapes
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Show 9 more resultsHide 9 results
Overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Procedural & Game Assets
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 10 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Products & Manufacturing
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 28 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Rendering & Simulation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 17 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Science & Visualization
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 9 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Text-only overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 78 text-only tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Vehicles & Machinery
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 11 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Visual-quality dimension score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Weighted rubric score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
CADGenBench · GenerationMecado · generation split · provider harnesses · reward · max effort · Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
CursorBench 3.2Anthropic Fable/Mythos 5.1 launch table · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSWE v1.112 results
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
max · official Datacurve leaderboard · task pass rate
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
mini-SWE / DeepSeek设置
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort
Show 2 more resultsHide 2 results
OpenAI launch table
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
EEBenchAtopile · provider harnesses · reward · max effort · Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI launch table
ExplorationBench22 related benchmarks · 22 results
AlienCode · M4 · fixed-probe control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · A4+O · complete rules after exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienCode · M0 · baseline of Best@3 trajectory
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · Best@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · direct answering control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · M4 · hindsight-replay control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
Show 16 more resultsHide 16 results
AlienCode · M4 · Mean@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · M4 · without-tool control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienCode · M4 · Worst@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienCode · O@M0 · complete rules before exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienCode · Rules correctly reported
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · A4+O · complete rules after exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · Correct refusal on unprovable tasks
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
AlienLogic · M0 · baseline of Best@3 trajectory
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · Best@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · direct answering control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · fixed-probe control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · hindsight-replay control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · Mean@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University, Tencent Hy / ExplorationBench authors · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · M4 · without-tool control
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · one matched control trajectory
AlienLogic · M4 · Worst@3 held-out accuracy
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · 3 independent autonomous trajectories
AlienLogic · O@M0 · complete rules before exploration
Reported by Fudan University / Tencent Hy / Tsinghua University · via BenchBoard docs
official 2026-10-13 leaderboard snapshot · 70 held-out tasks in this world · 4 exploration rounds · 3 answers/task · max reasoning · complete-rule reference or auxiliary diagnostic
HealthBenchOpus 5.5 System Card · adaptive thinking · max effort unless stated · raw · same Opus 5.5 card setup · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Opus 5.5 System Card · adaptive thinking · max effort unless stated · same Opus 5.5 card setup
Opus 5 System Card capability summary · adaptive thinking · max effort unless noted
System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted
Source: Clinical Benchmarks data docs · Reported by the model's developer. The source relaying it did not verify it. claim · Jul 2026
Setting not stated
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MLE-Bench Lite · HumanRankAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · Claude Code · 12-hour task limit · HumanRank score · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_表現
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
anthropic/claude-opus-5: adaptive-thinking-max
NL2Repo-Bench2 results
Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSeek V4.1 launch chart · settings unspecified · launch-page table
Protocol TroubleshootingOpus 5.5 System Card · adaptive thinking · max effort unless stated · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RecreationBench paper26 related benchmarks · 26 results
Web · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score
Android · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Android · nominal 50-task split · platform-specific score
macOS · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · macOS · nominal 50-task split · platform-specific score
Show 20 more resultsHide 20 results
macOS · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · macOS · nominal 50-task split · platform-specific score
macOS · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · macOS · nominal 50-task split · platform-specific score
macOS · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · macOS · nominal 50-task split · platform-specific score
Overall · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Estimated API cost per task
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · estimated mean API cost per task · 90% cache reads assumed
Overall · Programmatic + visual mean
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Ubuntu · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Web · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score
Web · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score
Web · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Web · nominal 50-task split · platform-specific score
Windows · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · max reasoning effort per site data · 1m context · 128k max output tokens · Windows · nominal 50-task split · platform-specific score
SingleCellBenchOpus 5.5 System Card · adaptive thinking · max effort unless stated · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SkillsBench8 related benchmarks · 8 results
Text-only (79 tasks)
Reported by Tencent Hy · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Hy4 official Benchmark Appendix · highest available reasoning setting · Claude Code · 79 self-contained text-only tasks · three-run average
Text-only (79 tasks) · OpenHands
Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Atria Table 1 / Appendix B · OpenHands within AgentCompass · 79 self-contained text-only tasks · three-run average · reasoning tiers and task-source commit not stated
Vals · With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
Vals · With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
Vals · With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
Vals · Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
Show 2 more resultsHide 2 results
Vals · Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
Vals · Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=anthropic/claude-opus-5 · provider=Anthropic · compute_effort=max · temperature=1 · max_output_tokens=128000
SpatialBench VerifiedOpus 5.5 System Card · adaptive thinking · max effort unless stated · Reported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-Marathon v1.1native provider harnesses · 8 trials/task · resolution rate · max effort · Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Toolathlon VerifiedReported by Anthropic · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals14 related benchmarks · 16 results
EMB
Source: Vals AI
CorpFin v2
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Show 9 more resultsHide 9 results
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MortgageTax
Source: Vals AI
Show 9 more resultsHide 9 results
Source: OpenRouter benchmark exports · Aug 2026
exa search · OpenRouter's search tool · up to 1 turn · high effort
exa search · OpenRouter's search tool · up to 25 turns · high effort
exa search · OpenRouter's search tool · up to 5 turns · high effort
parallel search · OpenRouter's search tool · up to 1 turn · high effort
parallel search · OpenRouter's search tool · up to 25 turns · high effort
parallel search · OpenRouter's search tool · up to 5 turns · high effort
perplexity search · OpenRouter's search tool · up to 1 turn · high effort
perplexity search · OpenRouter's search tool · up to 25 turns · high effort
perplexity search · OpenRouter's search tool · up to 5 turns · high effort
Workspace-Bench · English Full · Atria runAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Full · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Workspace-Bench · English Lite · Atria runAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · AgentCompass · English Lite · two-hour limit · 2 CPUs / 8 GiB · Seed 2.0 Lite judge · GPT in Codex, others in Claude Code · metric subtype unstated · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ZeroBench · MainDeepSeek V4.1 launch chart · settings unspecified · with tools · Reported by DeepSeek · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
τ³-Bench · Banking Knowledge · Atria runAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit · Reported by Shanghai AI Laboratory · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

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) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · 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. · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · 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) · ExploitGym leaderboard (Wang et al., UC Berkeley), arXiv:2605.11086. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only, and task data keeps its upstream licences. Literal exploit counts; hidden rows omitted. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here. · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · Hugging Face official benchmark leaderboards; licence varies by benchmark · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Also known as: claude-opus-5, aihubmix/claude-opus-5, anthropic-claude-opus-5, anthropic.claude-opus-5, anthropic.claude-opus-5-v1, anthropic/claude-opus-5, anthropic/claude-opus-5-batch, anthropic/claude-opus-5-fast, anthropic/claude-opus-5:batch, apac.anthropic.claude-opus-5, au.anthropic.claude-opus-5, aws-bedrock/claude-opus-5, azure_ai/claude-opus-5, bedrock/claude-opus-5, bedrock/claude-opus-5@eu-central-1, bedrock/claude-opus-5@eu-north-1, bedrock/claude-opus-5@eu-west-1, bedrock/claude-opus-5@eu-west-3, bedrock/us-gov-east-1/anthropic.claude-opus-5, bedrock/us-gov-west-1/anthropic.claude-opus-5, bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5, claude opus 5, claude opus 5 fast, claude-opus-5-fast, claude-opus-5-high, claude-opus-5-max, claude-opus-5-thinking, claude-opus-5@default, claude-opus-5@eu, databricks/databricks-claude-opus-5, deepinfra/anthropic/claude-opus-5, eu.anthropic.claude-opus-5, eu.anthropic.claude-opus-5-v1, github_copilot/claude-opus-5, global.anthropic.claude-opus-5, global.anthropic.claude-opus-5-v1, jp.anthropic.claude-opus-5, perplexity/anthropic/claude-opus-5, regional.anthropic.claude-opus-5, snowflake/claude-opus-5, us-gov.anthropic.claude-opus-5, us.anthropic.claude-opus-5, us.anthropic.claude-opus-5-v1, vertex/claude-opus-5, vertex/claude-opus-5@eu, vertex/claude-opus-5@us, vertex_ai/claude-opus-5, vertex_ai/claude-opus-5@default

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