Muse Spark 1.3vsKimi K3
Muse Spark 1.3 | Kimi K3 | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 2.8T |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 1M | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $3.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $15.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.30 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $2.60Sail Research |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $13.00Sail Research |
| Benchmarks | ||
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 75.4% | 69% |
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. | 88.8% | 88.3% |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 64.9% | 52.9% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1754 | 1668 |
| BenchmarksPublished by one model only | ||
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. | — | 73% |
DeepSWE 1.0Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | — | 67.5% |
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. | — | 85% |
Supabase Evals · with skillsSupabase coding — Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | — | 78.3% |
Supabase Evals · no skillsSupabase coding — The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | — | 81.2% |
SWEAtlas CodeBase QnACodebase understanding — Questions about how an unfamiliar codebase actually works — where something is handled, what a change would touch — answered by reading the repository rather than editing it. Tests understanding rather than patch-writing. Higher is better. | 59.4% | — |
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. | — | 84.2% |
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. | — | 73.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 91.2% |
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. | 89.4% | — |
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. | — | 43.5% |
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. | — | 56% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 93.5% |
Agentic IF Index (Internal)Instruction following — Meta's internal measure of whether a model keeps following the instructions it was given while working as an agent — over a long run of tool calls, not just in a single reply. Higher is better. | 57.8% | — |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | 66.9% | — |
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. | 49.4% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 84.8% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 81.6% |
MRCR · 256k-512kLong context — Tests whether the AI can find specific details buried inside a very long document, here across inputs of roughly 256k to 512k tokens — several books' worth of text. Higher is better. | 98.5% | — |
MRCR · 512k-1MLong context — The same buried-detail retrieval test run on even longer inputs, from roughly 512k up to a million tokens. Scores usually slip as the document grows, so read it against the shorter span above. Higher is better. | 98.1% | — |
| Overview | ||
| Company | Meta | Moonshot AI |
| Release date | Sep 2 2026 | Jul 16 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Muse Spark 1.3vsClaude Fable 5.1Kimi K3vsClaude Fable 5.1Muse Spark 1.3vsGPT-5.6 SolKimi K3vsGPT-5.6 SolMuse Spark 1.3vsGemini 3.8 FlashKimi K3vsGemini 3.8 FlashMuse Spark 1.3vsGrok 4.6Kimi K3vsGrok 4.6Muse Spark 1.3vsDeepSeek-V4-Pro-0813Kimi K3vsDeepSeek-V4-Pro-0813Muse Spark 1.3vsMistral Medium 3.5Kimi K3vsMistral Medium 3.5
Frequently asked questions
Muse Spark 1.3 leads Kimi K3 on 4 of the 4 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 2.1, JobBench, GDPval-AA v2). Only Kimi K3 has a verified first-party API price: $3.00 per million input tokens and $15.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark 1.3. Kimi K3 shipped 48 days before Muse Spark 1.3, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Muse Spark 1.3) vs 1M (Kimi K3). Muse Spark 1.3 is proprietary, while Kimi K3 is open weight.
On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs Kimi K3 at 69%. On Terminal-Bench 2.1, Muse Spark 1.3 leads at 88.8% vs Kimi K3 at 88.3%. On JobBench, Muse Spark 1.3 leads at 64.9% vs Kimi K3 at 52.9%. On GDPval-AA v2, Muse Spark 1.3 leads at 1754 vs Kimi K3 at 1668.
Muse Spark 1.3 was released by Meta on Sep 2 2026.
Kimi K3 was released by Moonshot AI on Jul 16 2026.
Muse Spark 1.3 leads on DeepSWE 1.1 — Muse Spark 1.3 75.4% vs Kimi K3 69%.
Only Kimi K3 has a verified first-party API price: $3.00 per million input tokens and $15.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark 1.3. Rates are pay-as-you-go API prices verified on August 18, 2026.
Muse Spark 1.3 has a 1M context window; Kimi K3 has 1M.
Muse Spark 1.3 is a proprietary model released by Meta. Kimi K3 is an open weight model released by Moonshot AI.