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. | 1M | 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 | ||
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. | 43.3% | 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. | 76.2% | 76% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.9% | 83.5% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 81.4% | 78.8% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 81% | 74% |
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. | 48% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 50% | — |
LiveCodeBench ProCompetitive programming — Elo rating on competitive programming problems in LiveCodeBench Pro | 2439 | — |
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% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 54.2% | — |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | 18.4% | — |
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% |
MCP Atlas · original harnessMulti-step tool use — pass rate under the original tool-use harness, before Scale changed the judge and retry handling in April 2026 | 54.1% | — |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | 85.3% | — |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | 98% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 59.2% | — |
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. | 37.5% | — |
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. | 45.8% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 31.1% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 95% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77% |
SimpleQA VerifiedKnowledge — accuracy on the vetted factual questions in SimpleQA Verified | 72.1% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | 91.8% | — |
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 |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | 77% | — |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | 26.3% | — |
| Overview | ||
| Company | Meta | |
| Release date | Nov 18 2025 | Aug 10 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 3.0 ProvsClaude Fable 5.2Muse GlimmervsClaude Fable 5.2Gemini 3.0 ProvsGPT-6.1 TerraMuse GlimmervsGPT-6.1 TerraGemini 3.0 ProvsGrok 4.7Muse GlimmervsGrok 4.7Gemini 3.0 ProvsDeepSeek-V4.1-Flash-1017Muse GlimmervsDeepSeek-V4.1-Flash-1017Gemini 3.0 ProvsMistral Large 4Muse GlimmervsMistral Large 4Gemini 3.0 ProvsKimi K3.1 ProMuse GlimmervsKimi K3.1 ProFrequently asked questions
Gemini 3.0 Pro leads Muse Glimmer on 4 of the 5 benchmarks they both report. Gemini 3.0 Pro shipped 265 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 3.0 Pro) vs 128k (Muse Glimmer). Gemini 3.0 Pro is closed, while Muse Glimmer is open weight.
On SWE-Bench Pro, Muse Glimmer leads at 51.2% vs Gemini 3.0 Pro at 43.3%. On SWE-Bench Verified, Gemini 3.0 Pro leads at 76.2% vs Muse Glimmer at 76%. On GPQA Diamond, Gemini 3.0 Pro leads at 91.9% vs Muse Glimmer at 83.5%. On CharXiv Reasoning, Gemini 3.0 Pro leads at 81.4% vs Muse Glimmer at 78.8%. On MMMU-Pro, Gemini 3.0 Pro leads at 81% vs Muse Glimmer at 74%.