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. | 671B | 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. | $0.27SiliconFlow | $0.30DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | $1.20DeepInfra |
| $104SiliconFlow · fp8 | $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. | 68.4% | 76% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 80.7% | 83.5% |
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 MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 57.8% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 74.9% | — |
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% |
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. | — | 22% |
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 | DeepSeek | Meta |
| Release date | Sep 22 2025 | Aug 10 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3.1 TerminusvsClaude Haiku 5.5Muse GlimmervsClaude Haiku 5.5DeepSeek V3.1 TerminusvsGPT-6.1 SolMuse GlimmervsGPT-6.1 SolDeepSeek V3.1 TerminusvsGemini 4 ArgonMuse GlimmervsGemini 4 ArgonDeepSeek V3.1 TerminusvsGrok 4.7Muse GlimmervsGrok 4.7DeepSeek V3.1 TerminusvsMistral Large 4Muse GlimmervsMistral Large 4DeepSeek V3.1 TerminusvsKimi K3Muse GlimmervsKimi K3Frequently asked questions
Muse Glimmer leads DeepSeek V3.1 Terminus on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek V3.1 Terminus shipped 322 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
DeepSeek V3.1 Terminus has 671B parameters, while Muse Glimmer has 30B. Context windows are 128k (DeepSeek V3.1 Terminus) vs 128k (Muse Glimmer).
On SWE-Bench Verified, Muse Glimmer leads at 76% vs DeepSeek V3.1 Terminus at 68.4%. On GPQA Diamond, Muse Glimmer leads at 83.5% vs DeepSeek V3.1 Terminus at 80.7%.