Compare / Muse Spark 1.3 vs Kimi K2 (0905)

Muse Spark 1.3 vs Kimi K2 (0905)

Which is cheaper, which is more capable, and which does better at each kind of work, from 11 results on 2 sources that measured both models.

MetaMuse Spark 1.3 Released 2 Sep 2026 · $1.25 in · $4.25 out
Moonshot AIKimi K2 (0905) Released 5 Sep 2025 · $0.60 in · $2.50 out
Muse Spark 1.3 wins 11Kimi K2 (0905) wins 0

Of the 11 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Meta vs Moonshot AI, every model from both labs.

Muse Spark 1.3 or Kimi K2 (0905)? The short answer

Pick Muse Spark 1.3 if quality matters most: it scores higher (Intelligence Index 48.1 against 15.3). Pick Kimi K2 (0905) if cost matters more: it costs 46% less per token.

  • Kimi K2 (0905) is cheaper: $1.07 against $2.00 per million tokens, 46% less.
  • Muse Spark 1.3 scores higher on the Artificial Analysis Intelligence Index: 48.1 against 15.3.
  • Muse Spark 1.3 is newer: released 2 Sep 2026, against 5 Sep 2025 for Kimi K2 (0905).
  • On third-party benchmarks, on the results both models have: Muse Spark 1.3 does better for reasoning and knowledge, writing and sticking to the facts.

Head to head

48.1
Intelligence Index
15.3
$2.00
Price per million tokens, blendedlower is better
$1.07
1,048,576
Context window, tokens
262,144

Every fact side by side

Muse Spark 1.3Kimi K2 (0905)
Price per million tokens$1.25 in · $4.25 out$0.60 in · $2.50 out
Blended (3 in : 1 out)$2.00$1.07
Cheapest host, blended––
Cached input, per million$0.15 cached input–
Intelligence Index48.115.3
Spring Prompt overall59–
Output speed, tokens a second254–
Context window1,048,576 tokens262,144 tokens
Released2 Sep 2026 (newer)5 Sep 2025
WeightsClosedOpen
Developer based inthe USChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 17 of 32 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 25 of 32 not measured
Marketing planningPlanning a year of ad spend without overspending 25 of 32 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 13 of 159 not measured
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 8 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 11 of 187 125 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 7 of 169 74 of 169
Sticking to the factsSummarising without inventing things, and factual answers 11 of 139 128 of 139
Speed under pressureGood decisions against a real clock (fast chess) 33 of 35 not measured

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureMuse Spark 1.3Kimi K2 (0905)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 8 · 113 of 387 measured 1,494max reasoning 1,419
Overall · Text factualityArena rating, higher is better 13 · 132 of 163 measured 1,480max reasoning 1,403
Business, management and finance · TextArena rating, higher is better 4 · 134 of 380 measured 1,505max reasoning 1,404
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 10 · 132 of 249 measured 48.1max reasoning 15.3
GPQA Diamond% of questions, higher is better 5 · 131 of 232 measured 94.1%xhigh reasoning 76.7%
Humanity's Last Exam% of questions, higher is better 13 · 186 of 250 measured 48.7%max reasoning 6.4%
Show all 11 results (5 more)
MeasureMuse Spark 1.3Kimi K2 (0905)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 22 · 119 of 385 measured 1,459max reasoning 1,381
Expert prompts · TextArena rating, higher is better 12 · 138 of 338 measured 1,529max reasoning 1,417
Instruction following · TextArena rating, higher is better 13 · 136 of 387 measured 1,486max reasoning 1,390
Writing, literature and language · TextArena rating, higher is better 19 · 133 of 386 measured 1,470max reasoning 1,382
Artificial Analysis reported by Artificial Analysis · 1 result
Long-context reasoning (AA-LCR)% of questions, higher is better 16 · 154 of 241 measured 83.0%max reasoning 53.0%

Quick answers

Is Muse Spark 1.3 better than Kimi K2 (0905)?

Pick Muse Spark 1.3 if quality matters most: it scores higher (Intelligence Index 48.1 against 15.3). Pick Kimi K2 (0905) if cost matters more: it costs 46% less per token.

Which is cheaper, Muse Spark 1.3 or Kimi K2 (0905)?

Kimi K2 (0905) is cheaper: $1.07 against $2.00 per million tokens, 46% less.

Which is better for reasoning and knowledge, Muse Spark 1.3 or Kimi K2 (0905)?

Muse Spark 1.3 ranks 11 of 187 models on sale for hard questions across science, maths and general knowledge, against 125 for Kimi K2 (0905).

Which is better for writing, Muse Spark 1.3 or Kimi K2 (0905)?

Muse Spark 1.3 ranks 7 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 74 for Kimi K2 (0905).

Which is better for sticking to the facts, Muse Spark 1.3 or Kimi K2 (0905)?

Muse Spark 1.3 ranks 11 of 139 models on sale for summarising without inventing things, and factual answers, against 128 for Kimi K2 (0905).

Which has the bigger context window, Muse Spark 1.3 or Kimi K2 (0905)?

Muse Spark 1.3: 1,048,576 tokens, against 262,144 for Kimi K2 (0905).

Run Muse Spark 1.3 and Kimi K2 (0905) on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.