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. | — | 7B/13B/70B |
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 | 4k |
| 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 | — |
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 | — |
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 | — |
| $3,600Anthropic list price | — | |
| These models have no shared benchmark scores. | ||
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% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 29.9% |
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% | — |
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% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 13.5% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | — | 57.4% |
HellaSwagReasoning — commonsense completion of short scenarios | — | 85.3% |
WinoGrandeReasoning — resolving ambiguous pronouns in context | — | 80.2% |
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. | — | 68.9% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 56.8% |
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% | — |
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% | — |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1785 | — |
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% | — |
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Nov 9 2026 | Jul 18 2023 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Fable 5.2vsGPT-6.1 TerraLLaMA 2vsGPT-6.1 TerraClaude Fable 5.2vsGemini 4 CarbonLLaMA 2vsGemini 4 CarbonClaude Fable 5.2vsGrok 4.7LLaMA 2vsGrok 4.7Claude Fable 5.2vsDeepSeek-V4.1-Flash-1017LLaMA 2vsDeepSeek-V4.1-Flash-1017Claude Fable 5.2vsMistral Large 4LLaMA 2vsMistral Large 4Claude Fable 5.2vsKimi K3.1 ProLLaMA 2vsKimi K3.1 ProFrequently asked questions
Claude Fable 5.2 and LLaMA 2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Claude Fable 5.2 has a verified first-party price for an available API: $8.00 per million input tokens and $40.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for LLaMA 2. LLaMA 2 shipped 1210 days before Claude Fable 5.2, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Fable 5.2) vs 4k (LLaMA 2). Claude Fable 5.2 is closed, while LLaMA 2 is open weight.
Direct benchmark comparisons are unavailable — Claude Fable 5.2 and LLaMA 2 don't publish scores on any of the same benchmarks.