Model comparison

Muse Spark 1.2 vs Reka Flash 3

Muse Spark 1.2 has enough public results to be ranked (#44); Reka Flash 3 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Muse Spark 1.2 Meta

49.8

Rank #44 Confirmed

Reka Flash 3 Reka

36.4

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Muse Spark 1.2 scores higher in 1 category and Reka Flash 3 in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.6 to 43.8.
  • Reka Flash 3 is cheaper at $0.10 / $0.20 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 66K.
  • Reka Flash 3 has downloadable open weights; the other is API-only.

Side by side

Muse Spark 1.2 and Reka Flash 3 specifications
Muse Spark 1.2Reka Flash 3
ProviderMetaReka
Noometry Index49.836.4
Released2026-08-052025-03-10
WeightsProprietaryOpen
Context window1.05M66K
Max output131K59K
Input $ / M tokens$1.25$0.10
Output $ / M tokens$4.25$0.20
Results tracked282

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

Category by category

Coding Not comparable

Muse Spark 1.2: 48.6 (#49), Reka Flash 3: —

Coding benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
DeepSWE54.9%—
LMArena WebDev1532—
FrontierSWE12%—
SciCode56.4%—
WeirdML60.3%—
LMArena Coding1497—

Agentic & Tool Use Too close to call

Muse Spark 1.2: 29.5 (#77), Reka Flash 3: 30.1

Agentic & Tool Use benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
APEX-Agents36.4%—
BALROG—29.2%
GDP.pdf16%—

Reasoning Not comparable

Muse Spark 1.2: 50.4 (#32), Reka Flash 3: —

Reasoning benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
SimpleBench74.5%—
NYT Connections (extended)79.2%—
CritPt17.7%—
LMArena Hard Prompts1490—
DTBench94.7%—
LMCA48.4%—
Epoch Capabilities Index155.18—

Math Not comparable

Muse Spark 1.2: 43.8 (#68), Reka Flash 3: —

Math benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
ProofBench43%—

Knowledge Not comparable

Muse Spark 1.2: 53.9 (#49), Reka Flash 3: —

Knowledge benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
SimpleQA Verified60.3%—
LMArena Expert1485—

Multimodal Not comparable

Muse Spark 1.2: 42.6 (#24), Reka Flash 3: —

Multimodal benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
LMArena Vision1304—

Multilingual Not comparable

Muse Spark 1.2: 57.4 (#10), Reka Flash 3: —

Multilingual benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
LMArena Non-English1479—
LMArena Chinese1519—
LMArena Russian1494—

Instruction Following Not comparable

Muse Spark 1.2: 77.1 (#30), Reka Flash 3: —

Instruction Following benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
LMArena Instruction Following1466—

Long Context Not comparable

Muse Spark 1.2: 45.4 (#35), Reka Flash 3: —

Long Context benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
LMArena Longer Query1483—

Writing & Preference Muse Spark 1.2 leads

Muse Spark 1.2: 72.6 (#14), Reka Flash 3: 43.8

Writing & Preference benchmarks
BenchmarkMuse Spark 1.2Reka Flash 3
EQ-Bench Creative Writing18401228
LMArena Text1486—
LMArena Creative Writing1444—
LMArena Multi-Turn1504—

Frequently asked questions

Is Muse Spark 1.2 better than Reka Flash 3?

Muse Spark 1.2 has enough public results to be ranked (#44); Reka Flash 3 does not yet, so treat this comparison as directional.

Which is cheaper, Muse Spark 1.2 or Reka Flash 3?

Reka Flash 3 is cheaper. It lists at $0.10 per million input tokens and $0.20 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 66K.

How many benchmarks do Muse Spark 1.2 and Reka Flash 3 share?

1 benchmark has published results for both models. Muse Spark 1.2 has 28 scored results on Noometry and Reka Flash 3 has 2.

Related comparisons

Go deeper