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. | — | 1.05T |
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. | $8.00 | $0.70 |
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. | $40.00 | $2.10 |
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 | $0.07 |
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. | — | $0.70Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.10Mistral |
| $3,600Anthropic list price | $245Mistral list price | |
| Benchmarks | ||
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. | 51.4% | 59.9% |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1785 | 1393 |
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. | — | 80% |
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. | — | 61.7% |
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. | 69.9% | — |
FrontierCode 2.0Agentic coding — whether a model’s code changes to open-source repositories would be merged by their maintainers (version 2.0); separate from FrontierCode v1.1 scores | 49.1% | — |
SWEAtlas CodeBase QnACodebase understanding — Questions about how an unfamiliar codebase actually works — where something is handled, what a change would touch — answered by reading the repository rather than editing it. Tests understanding rather than patch-writing. Higher is better. | — | 59.4% |
AA Coding Agent IndexAgentic coding — Artificial Analysis' overall score for coding agents, combining three coding benchmarks with what each run costs and how many tokens it burns. It rates a model paired with a particular agent harness rather than the model alone, so the same model scores differently in different tools. Higher is better. | — | 48 |
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. | — | 41% |
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. | 74.6% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 84.5% |
RoboDojo SimRobotics — control of a simulated two-arm robot from camera images, average success rate | 64.9% | — |
WANDR (relaxed score)Agentic search — agentic web search, relaxed scoring | 82.1% | — |
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. | 74.2% | — |
OSWorld 2.1 · offlineAgentic 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. | 89.3% | — |
AA-Briefcase v1.1 (rubric)Knowledge work — Artificial Analysis agentic office-work eval, v1.1 rubric score; separate from the Elo rating | 66.1% | — |
Remote Labor Index (RLI)Knowledge work — real paid remote-work projects, scored on the share completed to client standard | 41.3% | — |
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. | 73.4% | — |
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. | — | 1026 |
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Nov 9 2026 | Oct 6 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Fable 5.2vsGPT-6.1 TerraMistral Large 4vsGPT-6.1 TerraClaude Fable 5.2vsGemini 4 CarbonMistral Large 4vsGemini 4 CarbonClaude Fable 5.2vsMuse EmberMistral Large 4vsMuse EmberClaude Fable 5.2vsGrok 4.7Mistral Large 4vsGrok 4.7Claude Fable 5.2vsDeepSeek-V4.1-Flash-1017Mistral Large 4vsDeepSeek-V4.1-Flash-1017Claude Fable 5.2vsKimi K3.1 ProMistral Large 4vsKimi K3.1 ProFrequently asked questions
Claude Fable 5.2 and Mistral Large 4 are evenly matched across the 2 benchmarks they both report (AutomationBench, AA-Briefcase v1.1). Mistral Large 4 is cheaper on both input and output: $0.70 vs $8.00 per million input tokens, and $2.10 vs $40.00 per million output tokens. Mistral Large 4 shipped 34 days before Claude Fable 5.2, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Fable 5.2) vs 1M (Mistral Large 4). Claude Fable 5.2 is closed, while Mistral Large 4 is open weight.
On AutomationBench, Mistral Large 4 leads at 59.9% vs Claude Fable 5.2 at 51.4%. On AA-Briefcase v1.1, Claude Fable 5.2 leads at 1785 vs Mistral Large 4 at 1393.