Skip to content

Muse Spark

MetaProprietaryReasoningVerifiedReleased Apr 8, 2026
Compare with GPT-5.3 CodexSource scores ↗
Overall score
60.5
Rank 56 of 222 · 50.7–70.3
Context window
262K
262,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
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. 1Instruction following#1093.3
  2. 2Multimodal#1284.4
  3. 3Knowledge#4576.2
  4. 4Reasoning57.1
  5. 5Agentic & tool use53.7
  6. 6Coding43.8
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (19)

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

Multimodal

MMMU-Pro80.4#11 of 48
CharXiv86.4#13 of 42
SimpleVQA71.3#8 of 17
ERQA64.7#11 of 16
ScreenSpot Pro84.1#6 of 15
ZeroBench33.0#3 of 8
MedXpertQA (MM)78.4#3 of 8

Agentic & tool use

Terminal-Bench 2.059.0#21 of 39
Claw-Eval63.8#15 of 36
CyberGym43.5#24 of 25
DeepSearchQA74.8#13 of 20

Knowledge

HLE50.4#17 of 69
HLE w/o tools42.8#19 of 43
HealthBench Hard42.8#1 of 12
MedXpertQA (Text)52.6#3 of 5

Coding

SWE-bench Verified77.4#32 of 98
SWE-bench Pro52.4#56 of 69
LiveCodeBench Pro80.0#3 of 6

Reasoning

ARC-AGI-242.5#35 of 41

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price———

Arena ratings

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

Text1474#26 · 14.2K votes
Vision1306#15 · 5.9K votes
Documents1444#29 · 1.1K votes

Speed

Measured by us through OpenRouter (median of trials).

Not available on OpenRouter, so we cannot measure it yet.

Related models

Same family

Similar score