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 | 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 | $0.30 |
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 | $2.50 |
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 | $0.03 |
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 | $0.15Google |
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 | $1.25Google |
| $2,250Anthropic list price | $185Google list price | |
| Benchmarks | ||
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. | 87% | 66% |
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. | 72.7% | 74% |
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. | — | 54.2% |
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. | 80.8% | — |
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. | 58% | — |
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. | — | 54% |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | — | 49% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.7% | — |
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. | 53% | — |
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. | 68.75% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.3% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1140 |
| Overview | ||
| Company | Anthropic | |
| Release date | Feb 5 2026 | Jul 21 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.6vsGPT-6.1 SolGemini 3.5 Flash-LitevsGPT-6.1 SolClaude Opus 4.6vsMuse Spark OpenGemini 3.5 Flash-LitevsMuse Spark OpenClaude Opus 4.6vsGrok 4.7Gemini 3.5 Flash-LitevsGrok 4.7Claude Opus 4.6vsDeepSeek-V4.1-Flash-1017Gemini 3.5 Flash-LitevsDeepSeek-V4.1-Flash-1017Claude Opus 4.6vsMistral Large 4Gemini 3.5 Flash-LitevsMistral Large 4Claude Opus 4.6vsKimi K3Gemini 3.5 Flash-LitevsKimi K3Frequently asked questions
Claude Opus 4.6 and Gemini 3.5 Flash-Lite are evenly matched across the 2 benchmarks they both report (BullshitBench v2, OSWorld-Verified). Gemini 3.5 Flash-Lite is cheaper on both input and output: $0.30 vs $5.00 per million input tokens, and $2.50 vs $25.00 per million output tokens. Claude Opus 4.6 shipped 166 days before Gemini 3.5 Flash-Lite, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Opus 4.6) vs 1M (Gemini 3.5 Flash-Lite).
On BullshitBench v2, Claude Opus 4.6 leads at 87% vs Gemini 3.5 Flash-Lite at 66%. On OSWorld-Verified, Gemini 3.5 Flash-Lite leads at 74% vs Claude Opus 4.6 at 72.7%.