Noometry

Model comparison

gpt-oss-20b vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 56× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

Last verified . 20 shared benchmarks.

gpt-oss-20b OpenAI

32.5

Rank #255 Confirmed

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 20 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.3 to 35.5.
  • The biggest single-benchmark swing is LMCA: 14.5% for gpt-oss-20b and 48.4% for Muse Spark 1.2.
  • gpt-oss-20b is cheaper at $0.018 / $0.09 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 131K.
  • gpt-oss-20b has downloadable open weights; the other is API-only.

Side by side

gpt-oss-20bMuse Spark 1.2
ProviderOpenAIMeta
Noometry Index32.550.3
Released2025-08-052026-08-05
WeightsOpenProprietary
Context window131K1.05M
Max output16K131K
Input $ / M tokens$0.018$1.25
Output $ / M tokens$0.09$4.25
Results tracked3431

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

Category by category

Coding Muse Spark 1.2 leads

gpt-oss-20b: 37.6 (#192), Muse Spark 1.2: 49.2 (#51)

Benchmarkgpt-oss-20bMuse Spark 1.2
SciCode34.4%56.4%
WeirdML40.9%60.3%
LMArena Coding13061495
DeepSWE—54.9%
LMArena WebDev—1533
FrontierSWE—12%
ALE-Bench566.05—

Agentic & Tool Use Muse Spark 1.2 leads

gpt-oss-20b: 9.3 (#154), Muse Spark 1.2: 29.4 (#87)

Benchmarkgpt-oss-20bMuse Spark 1.2
Terminal-Bench3.4%—
APEX-Agents—36.4%
GDP.pdf—16%

Reasoning Muse Spark 1.2 leads

gpt-oss-20b: 19.3 (#261), Muse Spark 1.2: 51.3 (#34)

Benchmarkgpt-oss-20bMuse Spark 1.2
CritPt1.4%17.7%
LMArena Hard Prompts12741486
DTBench68%94.7%
LMCA14.5%48.4%
Epoch Capabilities Index137.82154.87
SimpleBench—74.5%
Kagi LLM Benchmark53.2%—
NYT Connections (extended)—79.2%
Chess Puzzles4%—

Math Muse Spark 1.2 leads

gpt-oss-20b: 39.4 (#103), Muse Spark 1.2: 46.4 (#70)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Math13171471
OTIS Mock AIME 2024-202565.3%—
ProofBench—43%
Omni-MATH56.5%—

Knowledge Muse Spark 1.2 leads

gpt-oss-20b: 34.6 (#195), Muse Spark 1.2: 54.1 (#53)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Expert12581480
GPQA Diamond60.8%—
SimpleQA Verified—60.3%
MMLU-Pro74%—
GPQA (HELM)59.4%—

Multimodal Not comparable

gpt-oss-20b: —, Muse Spark 1.2: 43.4 (#25)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Vision—1305

Multilingual Muse Spark 1.2 leads

gpt-oss-20b: 42.2 (#197), Muse Spark 1.2: 57.1 (#11)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Non-English12681478
LMArena Chinese13141511
LMArena Russian12781487
LMArena Spanish12671498
LMArena French—1513
LMArena German1255—
LMArena Japanese1244—
LMArena Korean1236—

Instruction Following Muse Spark 1.2 leads

gpt-oss-20b: 61.8 (#240), Muse Spark 1.2: 76.7 (#36)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Instruction Following12361461
IFEval73.2%—

Long Context Muse Spark 1.2 leads

gpt-oss-20b: 37.9 (#209), Muse Spark 1.2: 45.2 (#48)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Longer Query12501475

Writing & Preference Muse Spark 1.2 leads

gpt-oss-20b: 35.5 (#265), Muse Spark 1.2: 72.3 (#14)

Benchmarkgpt-oss-20bMuse Spark 1.2
LMArena Text12871482
LMArena Creative Writing12011449
EQ-Bench Creative Writing6661840
LMArena Multi-Turn12681494
WildBench73.7%—

Frequently asked questions

Is gpt-oss-20b better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 32.5 on the Noometry Index. gpt-oss-20b costs 56× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

Which is cheaper, gpt-oss-20b or Muse Spark 1.2?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

Is gpt-oss-20b or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 37.6 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 131K.

How many benchmarks do gpt-oss-20b and Muse Spark 1.2 share?

20 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper