Muse Spark 1.3 (Max)

MetaProprietary

Muse Spark 1.3 (Max) is a vision-language model from Meta. It ranks 12 of 167 on LMArena’s overall vision board with 1308±9 from 5,392 votes. Its best category is Diagrams (#10 of 123). License: Proprietary.

Key figures

LMArena · Overall1308±9#12 / 167 · Votes 5,392
OCR1319±10#12 / 123 · Votes 3,701
Diagrams1330±17#10 / 123 · Votes 1,352
Homework1296±21#40 / 118 · Votes 752
Creative writing1296±28#21 / 104 · Votes 493
Humor1288±39#21 / 93 · Votes 222
English1298±15#17 / 167 · Votes 1,877
Chinese1368±34#12 / 128 · Votes 290
Developer
Meta
License
Proprietary
First seen (our snapshots)
2026-10-26

No data: Captioning, Entity recognition.

Who it suits

  • Overall #12 of 167: upper half.
  • Strongest category: Diagrams (#10 of 123).
  • Proprietary; used through Meta’s apps or API.

Neighbours on the overall board

#ModelScoreVotesLicenseΔ vs this model
9Claude Opus 4.7 (High) Anthropic131322,731Proprietary+5
10Qwen3.8-Max Alibaba13139,957Proprietary+5
11Claude Opus 4.6 Anthropic131226,841Proprietary+4
12Muse Spark 1.3 (Max) Meta13085,392Proprietary
13Gemini 3.5 Flash (High) Google130813,862Proprietary+0
14Gemini 3.5 Flash (Medium) Google130614,061Proprietary-2
15Muse Spark Meta13065,865Proprietary-2

Alternatives · More from Meta

#ModelScoreVotesLicense
15Muse Spark Meta13065,865Proprietary
17Muse Spark 1.2 (xHigh) Meta13041,948Proprietary
19Muse Spark 1.3 (xHigh) Meta13024,897Proprietary
26Muse Spark 1.1 Meta129312,804Proprietary
122Llama 4 Maverick 17B 128E Instruct Meta11426,923Llama 4

Alternatives · Top open-weight models

#ModelScoreVotesLicense
24GLM-5.3-Flash Z.ai129416,254MIT
34Kimi K2.6 Moonshot AI128216,368Modified MIT
38DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek12784,100MIT
39Gemma 4 31B Google127640,219Apache 2.0
44Qwen3.8-27B Alibaba12697,614Apache 2.0

How to read these scores

  • If two scores differ by less than their ± intervals, the models are statistically close.
  • Each category board is computed independently; do not compare scores across categories.
  • Models with few votes move more; ranks of new entries may change.

FAQ

Where does Muse Spark 1.3 (Max) rank among vision models?

Overall rank 12 (1308); OCR rank 12 (1319); Diagrams rank 10 (1330); Homework rank 40 (1296); Creative writing rank 21 (1296); Humor rank 21 (1288); English rank 17 (1298); Chinese rank 12 (1368) (LMArena, data as of Oct 26, 2026).

How good is Muse Spark 1.3 (Max) at OCR?

Muse Spark 1.3 (Max) ranks 12 of 123 on LMArena’s OCR board with 1319 (3,701 votes).

Is Muse Spark 1.3 (Max) better with Chinese or English prompts?

Chinese board: #12 of 128 (1368); English board: #17 of 167 (1298). The boards are computed separately, so compare ranks rather than scores.

Is Muse Spark 1.3 (Max) open-weight?

No. LMArena lists it as Proprietary; it is available through Meta’s apps or API.

How far is Muse Spark 1.3 (Max) from #1?

#1 overall is Claude Fable 5 (High) (1325); Muse Spark 1.3 (Max) has 1308, 17 points behind.

Sources

LMArena data published Oct 19, 2026.

Synced here Oct 26, 2026.

Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.