Noometry

Model comparison

Kimi K2.6 vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 47.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Kimi K2.6 Moonshot AI

47.5

Rank #52 Confirmed

Muse Spark 1.2 Meta

49.8

Rank #44 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Kimi K2.6 scores higher in 3 categories and Muse Spark 1.2 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2.6 leads 56.8 to 43.8.
  • The biggest single-benchmark swing is ProofBench: 16% for Kimi K2.6 and 43% for Muse Spark 1.2.
  • Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
  • Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
  • Kimi K2.6 has downloadable open weights; the other is API-only.

Side by side

Kimi K2.6Muse Spark 1.2
ProviderMoonshot AIMeta
Noometry Index47.549.8
Released2026-04-202026-08-05
WeightsOpenProprietary
Context window262K1.05M
Max output262K131K
Input $ / M tokens$0.95$1.25
Output $ / M tokens$4$4.25
Results tracked5128

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Kimi K2.6 leads

Kimi K2.6: 50.5 (#41), Muse Spark 1.2: 48.6 (#49)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena WebDev15091532
SciCode53.5%56.4%
WeirdML55.9%60.3%
LMArena Coding14881497
SWE-bench Verified76.7%—
DeepSWE—54.9%
FrontierSWE—12%
ALE-Bench1,093—

Agentic & Tool Use Muse Spark 1.2 leads

Kimi K2.6: 21.8 (#128), Muse Spark 1.2: 29.5 (#77)

BenchmarkKimi K2.6Muse Spark 1.2
GDP.pdf12%16%
APEX-Agents—36.4%
OSWorld 2.04.6%—
ExploitBench18.4%—
GBAEval0.9%—
Vending-Bench 26,205—

Reasoning Muse Spark 1.2 leads

Kimi K2.6: 39.6 (#51), Muse Spark 1.2: 50.4 (#32)

BenchmarkKimi K2.6Muse Spark 1.2
NYT Connections (extended)87.2%79.2%
CritPt8%17.7%
LMArena Hard Prompts14701490
DTBench90.9%94.7%
LMCA37.3%48.4%
Epoch Capabilities Index151.03155.18
SimpleBench—74.5%
Chess Puzzles26%—
EBR-Bench2.4%—
Mystery Game Puzzles18%—

Math Kimi K2.6 leads

Kimi K2.6: 56.8 (#34), Muse Spark 1.2: 43.8 (#68)

BenchmarkKimi K2.6Muse Spark 1.2
ProofBench16%43%
FrontierMath (Tiers 1-3)57.2%—
FrontierMath Tier 425.6%—
MathArena Final-Answer Competitions72.9%—
OTIS Mock AIME 2024-202596.1%—
LMArena Math1475—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Too close to call

Kimi K2.6: 53.9 (#48), Muse Spark 1.2: 53.9 (#49)

BenchmarkKimi K2.6Muse Spark 1.2
SimpleQA Verified34.9%60.3%
LMArena Expert14911485
GPQA Diamond90.8%—
Vectara Hallucination Rate10.8%—

Multimodal Muse Spark 1.2 leads

Kimi K2.6: 31.8 (#95), Muse Spark 1.2: 42.6 (#24)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena Vision12821304
Blueprint-Bench 23.9%—
Furniture Assembly21.7%—
LMArena Document1451—

Multilingual Muse Spark 1.2 leads

Kimi K2.6: 55.1 (#35), Muse Spark 1.2: 57.4 (#10)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena Non-English14461479
LMArena Chinese15211519
LMArena Russian14461494
LMArena French1471—
LMArena German1449—
LMArena Japanese1442—
LMArena Korean1428—
LMArena Spanish1463—

Instruction Following Too close to call

Kimi K2.6: 76.5 (#40), Muse Spark 1.2: 77.1 (#30)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena Instruction Following14511466

Long Context Too close to call

Kimi K2.6: 44.9 (#50), Muse Spark 1.2: 45.4 (#35)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena Longer Query14681483

Writing & Preference Muse Spark 1.2 leads

Kimi K2.6: 68.7 (#25), Muse Spark 1.2: 72.6 (#14)

BenchmarkKimi K2.6Muse Spark 1.2
LMArena Text14551486
LMArena Creative Writing14341444
EQ-Bench Creative Writing17251840
LMArena Multi-Turn14531504
EQ-Bench 41202—

Frequently asked questions

Is Kimi K2.6 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 47.5 on the Noometry Index.

Which is cheaper, Kimi K2.6 or Muse Spark 1.2?

Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

Is Kimi K2.6 or Muse Spark 1.2 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 48.6 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

How many benchmarks do Kimi K2.6 and Muse Spark 1.2 share?

24 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Muse Spark 1.2 has 28.

Related comparisons

Go deeper