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. | 9B/27B | — |
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. | 8k | 1M |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.10 |
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. | — | $0.50 |
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. | — | $0.004 |
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. | $0.65NextBit | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.65NextBit | — |
| $163NextBit · int4 | $45.00Meta list price | |
| These models have no shared benchmark scores. | ||
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. | — | 46 |
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. | 51.8% | — |
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. | — | 40.9% |
MATHReasoning — accuracy on the original competition mathematics test set | 42.3% | — |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | 71.4% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 86.4% | — |
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. | 75.2% | — |
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. | 74% | — |
AutomationBench (Artificial Analysis)Business workflows — The same business-workflow test, run by Artificial Analysis rather than by the lab, and graded strict pass@1: a workflow counts only if the whole of it is right on the first attempt. Read it as a separate board from the lab-run AutomationBench scores. Higher is better. | — | 37.8% |
AA Intelligence Index v5.0Overall intelligence — Artificial Analysis composite intelligence index, version 5.0 with tools; separate from earlier index editions | — | 36 |
GDP.PDF (Artificial Analysis)Document comprehension — The same professional-PDF test, run by Artificial Analysis rather than by the lab. Read it as a separate board from the lab-run GDP.PDF scores. Higher is better. | — | 22.8% |
| Overview | ||
| Company | Meta | |
| Release date | Jun 27 2024 | Nov 9 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Gemma 2vsClaude Fable 5.2Muse EmbervsClaude Fable 5.2Gemma 2vsGPT-6.1 TerraMuse EmbervsGPT-6.1 TerraGemma 2vsGrok 4.7Muse EmbervsGrok 4.7Gemma 2vsDeepSeek-V4.1-Flash-1017Muse EmbervsDeepSeek-V4.1-Flash-1017Gemma 2vsMistral Large 4Muse EmbervsMistral Large 4Gemma 2vsKimi K3.1 ProMuse EmbervsKimi K3.1 ProFrequently asked questions
Gemma 2 and Muse Ember don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Muse Ember has a verified first-party price for an available API: $0.10 per million input tokens and $0.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Gemma 2. Gemma 2 shipped 865 days before Muse Ember, so benchmark comparisons should account for the intervening progress.
Context windows are 8k (Gemma 2) vs 1M (Muse Ember). Gemma 2 is open weight, while Muse Ember is closed.
Direct benchmark comparisons are unavailable — Gemma 2 and Muse Ember don't publish scores on any of the same benchmarks.