Compare Models

Muse Spark 1.3 Max

Muse Spark 1.3 Max is a model from Meta, released September 5, 2026. Its best result is #1 of 82 on Legal Research Bench.

Release Date: Sep 5, 2026

Developer Meta  🇺🇸
Context Window 1M
Max Output Tokens 131k
Token Costs (in/out) $1.25/4.25
Weights Private
Input Modalities

Accuracy

41.62 %

Avg. Cost (In/Out)

$ 1.25 / $ 4.25

Latency

326 min 36 s

Vals Index
BenchmarksAccuracyRankings
Vals RSI Index

19.64%

18/25
Code Migration

47.41%

±4.26
15/79
CUA-bench

5.83%

7/9
CyberBench v1.1

72.74%

±5.67
16/47
EMB

67.43%

±3.06
16/76
Finance Agent (v2)

59.96%

±2.06
5/80
Legal Research Bench

55.29%

±3.46
1/82
MysteryMechanism

36.04%

±3.23
9/28
ProofBench v1.1

58.00%

±4.96
24/51
SRE Bench

3.82%

±1.19
21/35
Tax Agent Bench

42.44%

±3.51
7/73
Vibe Code Bench 1-100

20.46%

±3.85
9/25
Vibe Code Bench v1.1

85.86%

±2.51
14/116
IOI

56.56%

±2.52
20/45
ProgramBench

2.50%

±1.11
9/64
SWE-bench Multimodal

43.13%

±2.26
12/20
Terminal-Bench 4.0

24.75%

±0.51
23/52
Terminal-Bench-Science

10.00%

±3.61
15/42
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : Meta
Temperature: 1
Top P: Default
Top K: Default
Max Output Tokens: 131,072
Reasoning Effort: max

Compared with

Muse Spark 1.3 Max vs GPT-5.6 Sol 14 shared benchmarks Muse Spark 1.3 Max vs GPT-6 Sol 12 shared benchmarks Muse Spark 1.3 Max vs DeepSeek V4.1 Flash 1017 4 shared benchmarks Muse Spark 1.3 Max vs GPT-6.1 Sol 13 shared benchmarks Muse Spark 1.3 Max vs Claude Fable 5 8 shared benchmarks Muse Spark 1.3 Max vs MiMo V2.6 Pro 12 shared benchmarks Muse Spark 1.3 Max vs GPT-6 Astra 15 shared benchmarks Muse Spark 1.3 Max vs Claude Opus 5 14 shared benchmarks Muse Spark 1.3 Max vs Claude Opus 4.8 7 shared benchmarks Muse Spark 1.3 Max vs Claude Sonnet 5.5 12 shared benchmarks