Skip to content

Muse Spark 1.1

MetaProprietaryReasoningVerifiedReleased Jul 9, 2026Input: text, image, video, file
Overall score
66.1
Rank 33 of 222 · 57.6–74.6
Context window
1M
1,000,000 tokens
Price per 1M tokens
$1.25 in · $4.25 out
Source: OpenRouter
Blended price
$2.00
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Knowledge#2490.8
  2. 2Multimodal81.9
  3. 3Reasoning78.4
  4. 4Agentic & tool use#3366.9
  5. 5Coding#3960.2
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (20)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Agentic & tool use

Terminal-Bench 2.180.0#31 of 68
MCP Atlas88.1#2 of 42
OSWorld-Verified80.8#9 of 35
JobBench54.7#11 of 34
CyberGym59.0#22 of 25
OSWorld 2.014.2#18 of 24
Toolathlon75.6#1 of 22
DeepSearchQA84.9#10 of 20
ExploitGym0.8#14 of 14
WebArena-Verified69.0#1 of 4
Cybench92.9#2 of 2

Multimodal

Design Arena Website1270#27 of 91
CharXiv88.4#11 of 42
BabyVision76.3#3 of 8

Knowledge

HLE62.1#4 of 69
HLE w/o tools52.2#6 of 43
HealthBench Professional59.3#12 of 16

Coding

SWE-bench Pro61.5#24 of 69
DeepSWE53.3#43 of 50

Reasoning

MRCR 1M54.1#3 of 4

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (OpenRouter)$1.25$4.25—
OpenRouter meta/muse-spark-1.1$1.25$4.25$0.15

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1478#22 · 42.8K votes
WebDev (coding)1542#46 · 8K votes
Vision1293#26 · 12.8K votes
Documents1465#18 · 4.9K votes

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Same family

Similar score