Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 124B |
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 | 128k |
| 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. | $2.00 | — |
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. | $10.00 | — |
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. | $0.20 | — |
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. | $2.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $10.00Amazon Bedrock | — |
| $900Anthropic list price | — | |
| These models have no shared benchmark scores. | ||
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. | 60% | — |
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. | 55.5% | — |
FrontierCode v1.1 (Main) · main splitAgentic 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. | 52.1% | — |
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. | 70.6% | — |
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. | 64.5% | — |
GDPval-AA v2.1Knowledge work — economically valuable knowledge work (v2.1, Crowd-BT Elo fit) | 1844 | — |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1811 | — |
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. | 61.6% | — |
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. | 1849 | — |
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Sep 28 2026 | Nov 18 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Sonnet 5.5vsGPT-6.1 SolPixtral Large 24.11vsGPT-6.1 SolClaude Sonnet 5.5vsGemini 4 ArgonPixtral Large 24.11vsGemini 4 ArgonClaude Sonnet 5.5vsMuse Spark OpenPixtral Large 24.11vsMuse Spark OpenClaude Sonnet 5.5vsGrok 4.7Pixtral Large 24.11vsGrok 4.7Claude Sonnet 5.5vsDeepSeek-V4.1-Flash-1017Pixtral Large 24.11vsDeepSeek-V4.1-Flash-1017Claude Sonnet 5.5vsKimi K3Pixtral Large 24.11vsKimi K3Frequently asked questions
Claude Sonnet 5.5 and Pixtral Large 24.11 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Claude Sonnet 5.5 has a verified first-party API price: $2.00 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Pixtral Large 24.11. Pixtral Large 24.11 shipped 679 days before Claude Sonnet 5.5, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Sonnet 5.5) vs 128k (Pixtral Large 24.11). Claude Sonnet 5.5 is closed, while Pixtral Large 24.11 is open weight.
Direct benchmark comparisons are unavailable — Claude Sonnet 5.5 and Pixtral Large 24.11 don't publish scores on any of the same benchmarks.