Compare AI models
| Specifications | ||
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. | 1M | — |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $5.00 | — |
Output priceWhat 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 | — |
Cached input priceA 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 | — |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $5.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | — |
| $2,250Anthropic list price | — | |
| Benchmarks | ||
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 24.5% | 58.6% |
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. | 83% | — |
Gray Swan IPI · k = 15Prompt 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. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | — | 0% |
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. | 0% | — |
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. | 64.3% | — |
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. | 87.6% | — |
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. | 80.5% | — |
SWE-sweepAgentic coding — subtask-weighted reward for software engineering with the mini-swe-agent harness | — | 9.6% |
FrontierSWE V2Ultra-long-horizon coding — Engineering problems that would occupy a person for days: systems implementation, performance work, scientific computing and AI research, with up to twenty hours per task. Partial credit is awarded, because finishing one outright is still rare. Higher is better. | — | 61.2% |
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. | 58% | — |
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. | — | 65.2% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 66.1% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 69.4% | — |
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. | — | 64.8% |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 79.1% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 79.3% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 73.1% | — |
RiemannBenchAdvanced mathematics — mathematical problem-solving evaluation published by Surge | — | 80% |
Humanity's Last Exam · no toolsMultidisciplinary 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. | 46.9% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 54.7% | — |
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. | 75.8% | — |
FrontierMath · Tier 1–3Advanced math — Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | 43.8% | — |
FrontierMath · Tier 4Advanced math — Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | 22.9% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.2% | — |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task October 17, 2026 v1.1 set, using ALE-Claw with a five-hour limit; separate from earlier ALE scores | — | 77.4% |
CWE-bench v1Security patching — Collinear AI’s programmatically graded security-patch pass@1 rate; separate from exploit-generation benchmarks | — | 71% |
ExploitGym (causal pass rate) · 10-hour budgetCybersecurity — share of tasks producing a verified exploit of the intended vulnerability, with mitigations off; not a count of solved instances | — | 54.8% |
ExploitGym (causal pass rate) · 6-hour budgetCybersecurity — share of tasks producing a verified exploit of the intended vulnerability, with mitigations off; not a count of solved instances | — | 53.5% |
SEC-bench Pro (JavaScript)Vulnerability discovery — pass@1 on the 183-task May 2026 JavaScript-engine split, averaged over three trials with the Antigravity harness | — | 88.2% |
OSWorld 2.1 (offline)Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.1, in its offline setting. Scores are not comparable with version 2.0. Higher is better. | — | 81.5% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 78% | — |
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. | — | 53.9% |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 51.5% | — |
AA Intelligence Index v5.0Overall intelligence — Artificial Analysis composite intelligence index, version 5.0 with tools; separate from earlier index editions | — | 59 |
Vals Index v2.2Professional work — Vals AI composite evaluation of professional tasks, version 2.2 | — | 70.4% |
Vending-Bench 2 (USD)Business simulation — ending bank balance in US dollars in Andon Labs’ vending-business simulation; higher is better | — | 16484 |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1753 | — |
GDPval (win/tie rate)Knowledge work — How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | 80.3% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 82.1% | — |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | — | 72.5% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 75.2% | — |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | — | 96.2% |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 59.3% | — |
| Overview | ||
| Company | Anthropic | |
| Release date | Apr 16 2026 | Oct 28 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.7vsGPT-6.1 TerraGemini 4 CarbonvsGPT-6.1 TerraClaude Opus 4.7vsMuse Spark OpenGemini 4 CarbonvsMuse Spark OpenClaude Opus 4.7vsGrok 4.7Gemini 4 CarbonvsGrok 4.7Claude Opus 4.7vsDeepSeek-V4.1-Flash-1017Gemini 4 CarbonvsDeepSeek-V4.1-Flash-1017Claude Opus 4.7vsMistral Large 4Gemini 4 CarbonvsMistral Large 4Claude Opus 4.7vsKimi K3.1 ProGemini 4 CarbonvsKimi K3.1 ProFrequently asked questions
Gemini 4 Carbon leads Claude Opus 4.7 on 1 of the 1 benchmark they both report (Blueprint-Bench 2). Only Claude Opus 4.7 has a verified first-party price for an available API: $5.00 per million input tokens and $25.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Gemini 4 Carbon. Claude Opus 4.7 shipped 195 days before Gemini 4 Carbon, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On Blueprint-Bench 2, Gemini 4 Carbon leads at 58.6% vs Claude Opus 4.7 at 24.5%.