Skip to content
Leaderboard / Meta

Muse Spark 1.2

Meta xHigh CLOSED Proprietary
Verdict

Muse Spark 1.2 is a solid mid-pack model: #83 of 406 by SIscope score. Strongest at chat quality, weaker at agents & tools. Mid-range on price.

SIscope score
70
#83 of 406
Human-vote rank
#18
of 419 · score 1483
Price per 1M tokens, blended
$2
$1.25 in · $4.25 out
Context window
1M
1,048,576 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsReasoningMathChatInstructions

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding80
Agents & tools16
Reasoning & knowledge90
Math93
Chat quality96
Following instructions91

What goes into each category · Compare with DeepSeek V4.1 Flash

Human-vote score over time

Text arena, recent updates.

147514831490Oct 15: 1483.6 (rank #15)Oct 20: 1482.4 (rank #17)Oct 22: 1481.9 (rank #17)Oct 28: 1482.7 (rank #18)Oct 15Oct 28

Coding votes over time

WebDev arena, recent updates.

152515331540Oct 16: 1533.7 (rank #48)Oct 18: 1533.8 (rank #49)Oct 19: 1533.8 (rank #51)Oct 22: 1533.5 (rank #51)Oct 23: 1533.2 (rank #52)Oct 27: 1533.6 (rank #53)Oct 28: 1533.7 (rank #54)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

SimpleQA Verified60%
Short factual questions; rewards not making things up
Better than 85% of 100 tested models. Run Aug 27, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
#18 of 41914831476–148911,724Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#54 of 15215341520–15472,155Oct 28, 2026
Vision arena
Questions about images, blind human votes
#17 of 16713041290–13191,948Oct 19, 2026
Agent arena
Real multi-step agent sessions
#48 of 57-7.7%-8.6–-6.9%54,988Nov 2, 2026

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input
$1.25
per 1M tokens
Output
$4.25
per 1M tokens
Blended
$2
3 in : 1 out, per 1M
Context window
1M
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (meta/muse-spark-1.2), Nov 4, 2026. Providers can charge differently.