AI Model Release Tracker

Claude Opus 5

Released

Claude Opus 5 is an AI model released by Anthropic on Friday, Jul 24 2026, 24 days after Claude Sonnet 5. It has a 1M token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover Gray Swan IPI, SWE-Bench Verified, SWE-Bench Multilingual, SWE-Bench Multimodal, Supabase Evals, Frontier-Bench v0.1, and 24 more.

API pricing

InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$5.00
Cached inputA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
$0.50
5 min cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate. This option keeps it for five minutes.
$6.25
1 hr cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate. This option keeps it for an hour, so it costs more than the five-minute one.
$10.00
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$25.00
  • Thinking is on by default.
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Verified October 19, 2026Read from platform.claude.com. Click the check to open the source.

Available from

Amazon Bedrock——$5.00$25.001M
Anthropic——$5.00$25.001M
Azureglobal—$5.00$25.001M
Claude Platform on AWS——$5.00$25.001M
Googleglobal—$5.00$25.001M
Amazon Bedrockeu-west-1—$5.50$27.501M
Amazon Bedrockus-east-1—$5.50$27.501M
Azureus—$5.50$27.501M
Googleeu—$5.50$27.501M
Googleus—$5.50$27.501M
Anthropic—fast$10.00$50.001M
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Checked October 22, 2026Third-party rates from openrouter.ai, not the lab’s own list price.

Benchmarks

Coding

SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better.via BenchLM
96%
#1
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better.
89.5%
#1
SWE-Bench MultimodalMultimodal coding — Real bug reports that arrive with pictures attached — a screenshot, a mockup, a page rendering wrongly — so the AI has to read the image as well as the code to work out what to fix. Higher is better.
59.4%
#1
Supabase EvalsSupabase coding — Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better.
92.8%with skills
89.9%no skills
with skills
#1
no skills
#2 of 11
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better.via ProgramBench
4.5%
#6 of 25
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
79.2%
#3 of 24
CursorBench 4.0Agentic coding — Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better.via CursorBench
46.6%
#7 of 18
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
68.8%
#15 of 36
FrontierCode v1.1 (Main)Agentic coding — A set of very hard, frontier-difficulty coding tasks an AI agent has to complete end to end. The score is the share of tasks in the main split it solves. Higher is better.
48%main split
#5 of 8
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better.
94%
#5 of 33

Terminal & CLI

Frontier-Bench v0.1Agentic computer work — A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better.
43.3%
#1
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better.via Terminal-Bench
51.82%
#8 of 29
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better.
29%
#6 of 7

Agentic & tool use

BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better.
90.8%
#4 of 31
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better.
74%
#3 of 10
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better.
26.9%
#18 of 19

Reasoning & science

BioMysteryBenchBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better.
49.4%hard
90.1%human solved
hard
#2 of 3
human solved
#1
Humanity's Last ExamMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better.
56.3%no tools
63.6%with tools
no tools
#2 of 24
with tools
#7 of 53
ARC-AGI-3Novel problem-solving — The third generation of the ARC-AGI series: instead of static puzzles, the AI is dropped into small interactive game-like environments it has never seen and has to figure out the rules and solve them on its own. Higher is better.
30.2%
#2 of 2
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better.via BenchLM
90.4%
#6 of 41

Knowledge work

GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo)
1861
#1
GDPval-AA v2.1Knowledge work — economically valuable knowledge work (v2.1, Crowd-BT Elo fit)
1708
#4 of 7
AA-BriefcaseKnowledge work — Artificial Analysis agentic office-work eval (Elo)
1685
#2 of 4

Healthcare

HealthBench ProfessionalHealth — Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better.
59.8%
#5 of 7

Multimodal

ChartographyChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better.
83.4%with tools
#3 of 6

Robustness

Gray Swan IPIPrompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better.
0.2%k = 1
1.6%k = 10
2%k = 15
k = 1
#1
k = 10
#1
k = 15
#2 of 14
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better.via CheatBench
45.3%
#3 of 13
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.
73%
#15 of 98

Community preference

threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.
1707
#8 of 29

Source: CursorBench, retrieved 28 September 2026 · Source: CheatBench, retrieved 25 September 2026 · Source: ProgramBench, retrieved 11 September 2026 · Source: Terminal-Bench, retrieved 30 August 2026 · Source: BenchLM, retrieved 24 August 2026. Other sources are identified on the linked benchmark pages.

Compare Claude Opus 5 with

Claude Opus 5

Suggested comparisons

Claude Opus 5vsClaude Haiku 5.5Claude Opus 5vsGPT-6.1 SolClaude Opus 5vsGemini 4 ArgonClaude Opus 5vsMuse Spark OpenClaude Opus 5vsGrok 4.7Claude Opus 5vsDeepSeek-V4.1-Flash-1017Claude Opus 5vsMistral Large 4Claude Opus 5vsKimi K3Claude Opus 5vsGLM-5.3-FlashClaude Opus 5vsQwen3.8-Max-0902Claude Opus 5vsNemotron 3.5 Super VL

About

Claude Opus 5 was released on July 24, 2026 as Anthropic's next Opus model. The company positioned it as an everyday option approaching Fable 5's capabilities at half Fable's token price. It became the default model on Claude Max and the highest-capability option on Claude Pro at launch.

Anthropic emphasized improved software engineering, knowledge work and checking results during longer tasks. Its launch evaluations varied effort settings to compare quality with cost. Those comparisons describe specific tasks and configurations; a lower token price and better token efficiency are separate factors in the total cost of completing work.

Frequently asked questions

Claude Opus 5 was released by Anthropic on Friday, Jul 24 2026.

All Anthropic releases

30 tracked