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. | 200k | 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. | $15.00Amazon Bedrock | $0.30DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $75.00Amazon Bedrock | $1.20DeepInfra |
| $6,750Amazon Bedrock | $120DeepInfra · bf16 | |
| 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. | 74.5% | 76% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.9% | 83.5% |
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. | 44.4% | 65.9% |
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. | 43% | — |
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% |
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. | 46.5% | — |
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 | 40.9% | — |
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% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77% |
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% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 77.1% | — |
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Aug 5 2025 | Aug 10 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.1vsGPT-6.1 TerraMuse GlimmervsGPT-6.1 TerraClaude Opus 4.1vsGemini 4 CarbonMuse GlimmervsGemini 4 CarbonClaude Opus 4.1vsGrok 4.7Muse GlimmervsGrok 4.7Claude Opus 4.1vsDeepSeek-V4.1-Flash-1017Muse GlimmervsDeepSeek-V4.1-Flash-1017Claude Opus 4.1vsMistral Large 4Muse GlimmervsMistral Large 4Claude Opus 4.1vsKimi K3.1 ProMuse GlimmervsKimi K3.1 ProFrequently asked questions
Muse Glimmer leads Claude Opus 4.1 on 3 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, OSWorld-Verified). Claude Opus 4.1 shipped 370 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.1) vs 128k (Muse Glimmer). Claude Opus 4.1 is closed, while Muse Glimmer is open weight.
On SWE-Bench Verified, Muse Glimmer leads at 76% vs Claude Opus 4.1 at 74.5%. On GPQA Diamond, Muse Glimmer leads at 83.5% vs Claude Opus 4.1 at 80.9%. On OSWorld-Verified, Muse Glimmer leads at 65.9% vs Claude Opus 4.1 at 44.4%.