Noometry

Model comparison

DeepSeek LLM 67B vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 24.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 8.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 99.2% for Muse Spark 1.3.
  • DeepSeek LLM 67B has downloadable open weights; the other is API-only.

Side by side

DeepSeek LLM 67BMuse Spark 1.3
ProviderDeepSeekMeta
Noometry Index24.954.8
Released2023-11-292026-09-02
WeightsOpenProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked1537

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

Category by category

Coding Muse Spark 1.3 leads

DeepSeek LLM 67B: 31.9 (#278), Muse Spark 1.3: 56.6 (#21)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Coding10961514
CursorBench—41.6%
LMArena WebDev—1657
SciCode—59.7%

Agentic & Tool Use Not comparable

DeepSeek LLM 67B: —, Muse Spark 1.3: 38.6 (#30)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%

Reasoning Muse Spark 1.3 leads

DeepSeek LLM 67B: 16.5 (#304), Muse Spark 1.3: 54.0 (#27)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
Chess Puzzles0%38%
LMArena Hard Prompts10701503
Epoch Capabilities Index110.5156.75
NYT Connections (extended)—85.1%
CritPt—26%
Mystery Game Puzzles—25%
DTBench—96.5%
LMCA—53.9%
Bench to the Future 3—0.14

Math Muse Spark 1.3 leads

DeepSeek LLM 67B: 8.7 (#324), Muse Spark 1.3: 73.1 (#21)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
OTIS Mock AIME 2024-20250.8%99.2%
LMArena Math11081494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
ProofBench—58%
MATH Level 56.4%—

Knowledge Muse Spark 1.3 leads

DeepSeek LLM 67B: 7.0 (#313), Muse Spark 1.3: 42.6 (#95)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
GPQA Diamond24.6%—
LMArena Expert—1516

Multimodal Not comparable

DeepSeek LLM 67B: —, Muse Spark 1.3: 43.7 (#22)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Vision—1309
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

DeepSeek LLM 67B: 29.4 (#267), Muse Spark 1.3: 57.4 (#8)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Non-English10731481
LMArena Chinese11321529
LMArena French—1524
LMArena German—1515
LMArena Japanese—1474
LMArena Korean—1501
LMArena Russian—1490
LMArena Spanish—1490

Instruction Following Muse Spark 1.3 leads

DeepSeek LLM 67B: 55.4 (#277), Muse Spark 1.3: 77.5 (#22)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Instruction Following10791477

Long Context Muse Spark 1.3 leads

DeepSeek LLM 67B: 33.1 (#265), Muse Spark 1.3: 45.6 (#32)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Longer Query10921488

Writing & Preference Muse Spark 1.3 leads

DeepSeek LLM 67B: 31.6 (#282), Muse Spark 1.3: 73.6 (#9)

BenchmarkDeepSeek LLM 67BMuse Spark 1.3
LMArena Text11051490
LMArena Creative Writing10671455
LMArena Multi-Turn10821482
EQ-Bench Creative Writing—1906

Frequently asked questions

Is DeepSeek LLM 67B better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 24.9 on the Noometry Index.

Is DeepSeek LLM 67B or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and Muse Spark 1.3 share?

13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper