Model comparison

Kimi K2.7 Code vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 43.3 on the Noometry Index.

Last verified October 11, 2026. 9 shared benchmarks.

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Muse Spark 1.2

Summary

They share 9 benchmarks with published results for both. Kimi K2.7 Code scores higher in 1 category and Muse Spark 1.2 in 4 categories; 4 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 39.0.
The biggest single-benchmark swing is DeepSWE: 30.5% for Kimi K2.7 Code and 54.9% for Muse Spark 1.2.
Kimi K2.7 Code 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 K2.7 Code has downloadable open weights; the other is API-only.

Side by side

Kimi K2.7 Code and Muse Spark 1.2 specifications
	Kimi K2.7 Code	Muse Spark 1.2
Provider	Moonshot AI	Meta
Noometry Index	43.3	50.3
Released	2026-06-12	2026-08-05
Weights	Open	Proprietary
Context window	262K	1.05M
Max output	262K	131K
Input $ / M tokens	$0.95	$1.25
Output $ / M tokens	$4	$4.25
Results tracked	19	31

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

Category by category

Coding Muse Spark 1.2 leads

Kimi K2.7 Code: 42.9 (#95), Muse Spark 1.2: 49.2 (#51)

Coding benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
DeepSWE	30.5%	54.9%
LMArena WebDev	1473	1533
SciCode	47.5%	56.4%
WeirdML	54.1%	60.3%
FrontierCode	30.1%	—
FrontierSWE	—	12%
LMArena Coding	—	1495
ALE-Bench	886.23	—

Agentic & Tool Use Muse Spark 1.2 leads

Kimi K2.7 Code: 24.0 (#122), Muse Spark 1.2: 29.4 (#87)

Agentic & Tool Use benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
APEX-Agents	37.6%	36.4%
GBAEval	0.9%	—
GDP.pdf	—	16%
Vending-Bench 2	5,083	—

Reasoning Muse Spark 1.2 leads

Kimi K2.7 Code: 39.0 (#61), Muse Spark 1.2: 51.3 (#34)

Reasoning benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
SimpleBench	57.9%	74.5%
CritPt	10%	17.7%
Epoch Capabilities Index	149.97	154.87
NYT Connections (extended)	—	79.2%
Chess Puzzles	21%	—
LMArena Hard Prompts	—	1486
DTBench	—	94.7%
LMCA	—	48.4%
Surface Evolver Bench	48.8%	—

Math Kimi K2.7 Code leads

Kimi K2.7 Code: 52.9 (#48), Muse Spark 1.2: 46.4 (#70)

Math benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
FrontierMath (Tiers 1-3)	54%	—
FrontierMath Tier 4	12.2%	—
OTIS Mock AIME 2024-2025	95.6%	—
ProofBench	—	43%
LMArena Math	—	1471

Knowledge Too close to call

Kimi K2.7 Code: 53.5 (#57), Muse Spark 1.2: 54.1 (#53)

Knowledge benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
SimpleQA Verified	36.5%	60.3%
GPQA Diamond	87.9%	—
LMArena Expert	—	1480

Multimodal Not comparable

Kimi K2.7 Code: —, Muse Spark 1.2: 43.4 (#25)

Multimodal benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
LMArena Vision	—	1305

Multilingual Not comparable

Kimi K2.7 Code: —, Muse Spark 1.2: 57.1 (#11)

Multilingual benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
LMArena Non-English	—	1478
LMArena Chinese	—	1511
LMArena French	—	1513
LMArena Russian	—	1487
LMArena Spanish	—	1498

Instruction Following Not comparable

Kimi K2.7 Code: —, Muse Spark 1.2: 76.7 (#36)

Instruction Following benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
LMArena Instruction Following	—	1461

Long Context Not comparable

Kimi K2.7 Code: —, Muse Spark 1.2: 45.2 (#48)

Long Context benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
LMArena Longer Query	—	1475

Writing & Preference Not comparable

Kimi K2.7 Code: —, Muse Spark 1.2: 72.3 (#14)

Writing & Preference benchmarks
Benchmark	Kimi K2.7 Code	Muse Spark 1.2
LMArena Text	—	1482
LMArena Creative Writing	—	1449
EQ-Bench Creative Writing	—	1840
LMArena Multi-Turn	—	1494

Frequently asked questions

Is Kimi K2.7 Code better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 43.3 on the Noometry Index.

Which is cheaper, Kimi K2.7 Code or Muse Spark 1.2?

Kimi K2.7 Code 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 K2.7 Code or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 42.9 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 K2.7 Code and Muse Spark 1.2 share?

9 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Muse Spark 1.2 has 31.