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. | 284B | 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. | $0.0434Wafer | $0.30DeepInfra |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.14Relace | $1.20DeepInfra |
| $21.00Relace · fp4 | $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. | 79% | 76% |
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. | 82.7% | 51.7% |
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. | 39% | — |
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% |
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% |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 70.3% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 73.2% | — |
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% |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 76.7% | — |
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. | 34.8% | — |
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. | 61.4% | — |
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% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77% |
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% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 25.1% | — |
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 | Jul 31 2026 | Aug 10 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Flash-0731vsClaude Fable 5.2Muse GlimmervsClaude Fable 5.2DeepSeek-V4-Flash-0731vsGPT-6.1 TerraMuse GlimmervsGPT-6.1 TerraDeepSeek-V4-Flash-0731vsGemini 4 CarbonMuse GlimmervsGemini 4 CarbonDeepSeek-V4-Flash-0731vsGrok 4.7Muse GlimmervsGrok 4.7DeepSeek-V4-Flash-0731vsMistral Large 4Muse GlimmervsMistral Large 4DeepSeek-V4-Flash-0731vsKimi K3.1 ProMuse GlimmervsKimi K3.1 ProFrequently asked questions
DeepSeek-V4-Flash-0731 leads Muse Glimmer on 2 of the 2 benchmarks they both report (SWE-Bench Verified, Terminal-Bench 2.1). DeepSeek-V4-Flash-0731 shipped 10 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash-0731 has 284B parameters, while Muse Glimmer has 30B. Context windows are 1M (DeepSeek-V4-Flash-0731) vs 128k (Muse Glimmer).
On SWE-Bench Verified, DeepSeek-V4-Flash-0731 leads at 79% vs Muse Glimmer at 76%. On Terminal-Bench 2.1, DeepSeek-V4-Flash-0731 leads at 82.7% vs Muse Glimmer at 51.7%.