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. | 30B | — |
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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
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. | $0.30DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.20DeepInfra | — |
| $120DeepInfra · bf16 | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.5% | 60% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 51.2% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76% | — |
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. | — | 92.4% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 51.7% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 75.5% | — |
DeepSearchQAAgentic browsing — Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better. | 74.6% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 22% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 90% |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | — | 83.9 |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 70% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 77% | — |
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. | — | 85.2% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 89.9% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 65.9% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 953 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 78.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 74% | — |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Aug 10 2026 | Sep 12 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Muse GlimmervsClaude Fable 5.2o1-minivsClaude Fable 5.2Muse GlimmervsGemini 4 Carbono1-minivsGemini 4 CarbonMuse GlimmervsGrok 4.7o1-minivsGrok 4.7Muse GlimmervsDeepSeek-V4.1-Flash-1017o1-minivsDeepSeek-V4.1-Flash-1017Muse GlimmervsMistral Large 4o1-minivsMistral Large 4Muse GlimmervsKimi K3.1 Proo1-minivsKimi K3.1 ProFrequently asked questions
Muse Glimmer leads o1-mini on 1 of the 1 benchmark they both report (GPQA Diamond). o1-mini shipped 697 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Muse Glimmer) vs 128k (o1-mini). Muse Glimmer is open weight, while o1-mini is closed.
On GPQA Diamond, Muse Glimmer leads at 83.5% vs o1-mini at 60%.