ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Head to head · tested 27 Oct 2026

Kimi K3.1 Pro vs Muse Spark Open: accuracy, speed and price

Similar accuracy; Muse Spark Open costs less per question.

MoonshotAIKimi K3.1 Pro77.5% score · #9$0.01 per question38 tok/sMetaMuse Spark Open77.5% score · #9$0.0045 per question220 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Kimi K3.1 Pro scored 77.5% and Muse Spark Open 77.5% on the same 80 questions, a gap within what chance alone could produce.
  • Muse Spark Open is 2.3× cheaper per question as billed ($0.0045 vs $0.01), reasoning tokens included.
  • Muse Spark Open generates text 5.8× faster: 220 tokens per second against 38.
  • Muse Spark Open starts answering sooner: 0.5 s to the first token, against 1.3 s for Kimi K3.1 Pro.

Which should you choose?

Choose Muse Spark Open for the lower cost per correct answer ($0.0058 against $0.014), faster streaming, a quicker first token, open weights you can run yourself and more hosts to choose from on OpenRouter (6 against 1).

Accuracy gap +0.0 points (z = 0.00). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

MeasureKimi K3.1 ProMuse Spark OpenEdge
Verification scoreHigher is better77.5%77.5%Too close to call
Cost per questionLower is better$0.01$0.0045Muse Spark Open
Output speedHigher is better38220Muse Spark Open
Time to first tokenLower is better1.3 s0.5 sMuse Spark Open
End-to-end response timeLower is better19.6 s3.2 sMuse Spark Open
Tokens per questionLower is better973964Similar
Context windowHigher is better1M1MSimilar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

Kimi K3.1 Pro first, Muse Spark Open second

Verification scorehigher is better
Kimi K3.1 Pro77.5%
Muse Spark Open77.5%
Cost per questionlower is better
Kimi K3.1 Pro$0.01
Muse Spark Open$0.0045
Output speedhigher is better
Kimi K3.1 Pro38
Muse Spark Open220
Time to first tokenlower is better
Kimi K3.1 Pro1.3 s
Muse Spark Open0.5 s
End-to-end response timelower is better
Kimi K3.1 Pro19.6 s
Muse Spark Open3.2 s
Tokens per questionlower is better
Kimi K3.1 Pro973
Muse Spark Open964
Context windowhigher is better
Kimi K3.1 Pro1M
Muse Spark Open1M

Score vs. cost per question

Both models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BMuse WonderGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-5.4GPT-6 Lunagpt-oss-120bLlama 4 Maverick

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

SpecificationKimi K3.1 ProMuse Spark Open
CreatorMoonshotAIMeta
Released23 Oct 202615 Oct 2026
Weights—Open weights
ReasoningYesYes
Inputtext, image, videotext, image, video, file, audio
Outputtexttext
Context window1M tokens1M tokens
Knowledge cutoff——
List price in / out per 1M$2 / $10$1.25 / $4.25
Blended price per 1M (3:1)$4.00$2.00
Cheapest hostMoonshot AI · $2 / $10Makora · $1.25 / $4.25
Hosts on OpenRouter16
Last tested25 Oct 202626 Oct 2026

Compare any two models →

Kimi K3.1 Pro vs Muse Spark Open: frequently asked questions

Is Kimi K3.1 Pro better than Muse Spark Open?
On accuracy they are statistically tied: Kimi K3.1 Pro scored 77.5% and Muse Spark Open 77.5% on the same 80 questions from open datasets. Similar accuracy; Muse Spark Open costs less per question.
Which is cheaper, Kimi K3.1 Pro or Muse Spark Open?
Muse Spark Open is cheaper: $0.0045 per question as billed, against $0.01. List prices: Kimi K3.1 Pro $2 in / $10 out, Muse Spark Open $1.25 in / $4.25 out per million tokens.
Which is faster, Kimi K3.1 Pro or Muse Spark Open?
Muse Spark Open is faster at 220 output tokens per second, against 38. Time to first token: 1.3 s for Kimi K3.1 Pro, 0.5 s for Muse Spark Open.
Which has the larger context window, Kimi K3.1 Pro or Muse Spark Open?
Both accept about the same amount of context: 1M and 1M tokens.