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. | 1B/3B/11B/90B | 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. | 128k | 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. | — | $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. | — | $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. | — | $0.07 |
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. | $0.05Parasail | $0.70Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.33Parasail | $2.10Mistral |
| $26.50Parasail · bf16 | $245Mistral 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. | — | 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% |
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 | — | 19.7% |
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% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 84.5% |
MATHReasoning — accuracy on the original competition mathematics test set | 68% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 86% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 86.9% | — |
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. | — | 59.9% |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | — | 1393 |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 57.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 60.3% | — |
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. | — | 1008 |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Sep 25 2024 | Oct 6 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 3.2vsClaude Fable 5.2Mistral Large 4vsClaude Fable 5.2LLaMA 3.2vsGPT-6.2 AstraMistral Large 4vsGPT-6.2 AstraLLaMA 3.2vsGemini 4 NeonMistral Large 4vsGemini 4 NeonLLaMA 3.2vsGrok 4.7Mistral Large 4vsGrok 4.7LLaMA 3.2vsDeepSeek-V4.1-Flash-1017Mistral Large 4vsDeepSeek-V4.1-Flash-1017LLaMA 3.2vsKimi K3.1 ProMistral Large 4vsKimi K3.1 ProFrequently asked questions
LLaMA 3.2 and Mistral Large 4 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Mistral Large 4 has a verified first-party price for an available API: $0.70 per million input tokens and $2.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for LLaMA 3.2. LLaMA 3.2 shipped 741 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.
LLaMA 3.2 has 1B/3B/11B/90B parameters, while Mistral Large 4 has 1.05T. Context windows are 128k (LLaMA 3.2) vs 1M (Mistral Large 4).
Direct benchmark comparisons are unavailable — LLaMA 3.2 and Mistral Large 4 don't publish scores on any of the same benchmarks.