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 | 117B |
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 | $0.03AkashML |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.20DeepInfra | $0.119PrimeIntellect |
| $120DeepInfra · bf16 | $13.50Venice · int4 | |
| Benchmarks | ||
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% | 62.4% |
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% | 80.1% |
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. | — | 12% |
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% | — |
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 · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 14.9% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 22% | — |
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. | — | 19% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 95.8% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92.5% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 77% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | — | 81.3% |
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. | — | 90% |
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% | — |
HealthBench · full setHealthcare — physician rubric score on the full set of the original HealthBench evaluation | — | 57.6% |
HealthBench · hardHealthcare — physician rubric score on the hard subset of the original HealthBench evaluation | — | 30% |
HealthBench · consensusHealthcare — physician rubric score on the consensus subset of the original HealthBench evaluation | — | 89.9% |
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 | Aug 5 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Muse GlimmervsClaude Fable 5.2gpt-oss-120bvsClaude Fable 5.2Muse GlimmervsGemini 4 Carbongpt-oss-120bvsGemini 4 CarbonMuse GlimmervsGrok 4.7gpt-oss-120bvsGrok 4.7Muse GlimmervsDeepSeek-V4.1-Flash-1017gpt-oss-120bvsDeepSeek-V4.1-Flash-1017Muse GlimmervsMistral Large 4gpt-oss-120bvsMistral Large 4Muse GlimmervsKimi K3.1 Progpt-oss-120bvsKimi K3.1 ProFrequently asked questions
Muse Glimmer leads gpt-oss-120b on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). gpt-oss-120b shipped 370 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Muse Glimmer has 30B parameters, while gpt-oss-120b has 117B. Context windows are 128k (Muse Glimmer) vs 128k (gpt-oss-120b).
On SWE-Bench Verified, Muse Glimmer leads at 76% vs gpt-oss-120b at 62.4%. On GPQA Diamond, Muse Glimmer leads at 83.5% vs gpt-oss-120b at 80.1%.