MetaUnited States· released Oct 2026

Muse Wonder

Name: Muse Wonder
Author: Meta

Ranked #15, tested so far in 4 of the 5 categories the Index averages.

Meta, United States. One of 7 models from this lab on the Index.

Third-party publishedHigh confidence (12+ comparable tests, 4+ Index categories)

Snapshot November 10, 2026

OpenCharts Index

71.5

Ranked #15 (14 to 18) of 80 · 28.5% behind the frontier on average · 17 comparable tests · 4 counting categories

Part of this Index is an estimate. On the 4 categories it is tested in, it averages 70.3. The rest is filled in from models tested in every category, because it has too few results to count there yet: Reasoning. Such estimates have been within 2.6 points about nine times in ten.

Its band runs from 68.2 to 74.1: where the Index could land once it is tested in every category, or if any single test were dropped. That covers #14 to #18, and neighbours inside that range are ties.

Needs more results (2 of 5 so far)

Averaging 78.5 on the 2 it has; the score opens at 4 of 5.

Distance to today's frontier on the hardest tests. Not a measure of intelligence.

What it's known for

Muse Wonder, in 17 results.

Strongest in math (85.1) and coding (69.6). It trails the frontier most in multimodal, 39.2% behind on average. No comparable result yet in knowledge. Between 25% and 30% behind the best published results, on average. Part of its Index is an estimate. It has too few results in reasoning for that category to count, so it is filled in from models tested in every category. On the categories that do count it averages 70.3. Across its band it could sit anywhere from #14 to #18.

Strongest category

Math

Competition and research mathematics, graded on the final answer or the proof.

85.1

Mock AIME 2024–202599.4% · 99% of best
FrontierMath (Tiers 1–3)82.1% · 86% of best
ProofBench84.0% · 84% of best
FrontierMath Tier 470.7% · 71% of best

Mean of 4 of the category's 4 comparable tests. Counts toward the Index.

Best single result

Mock AIME 2024–2025

Solve competition mathematics problems that have a single exact integer answer.

99.4%

99.4% of the best (100.0%) · #15 of 98.

Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.

Where it trails

EBR-bench

Play a little-known card-based adventure game ten times through a text interface, keeping notes, and score on the last two games.

31.4%

65.3% behind the best published result (90.5%) · #14 of 30.

Getting better at an unfamiliar job by doing it is what people do in their first weeks at work. This checks whether practice helps a model at all.

Not measured yet

No comparable result yet in this category. A blank is a blank, never a zero, and it does not lower the Index.

Knowledge

Covered, but not averaged into the Index:

Reasoning2 of 8 tests · needs 4 · mean 65.2
Human preferencesingle-test category, shown beside the Index · 95.7

Every score, with its source

See it at work

What Muse Wonder was asked to do, and how it did.

Every test it has taken, by category, with the kind of task it faced, who produced the number and where the result landed against the best published one. The examples are original and illustrative, never items from the datasets themselves.

Human preference · mean 95.7 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it

Text ArenaLeaderboard

Answer the same prompt as a rival model; real users vote blind on which answer they prefer.

1,511

48% expected win rate against the board leader (1,526)
#3 of 113

max · board 2026-11-09

Source: Arena

Every result is read against the best published one on its test: percent scores as a share of the best above chance, Arena ratings as the expected win rate against the board leader, open-ended values on a log scale. Sitting a harder exam never lowers a model. Every number links to the publisher that produced it.

Head to head

Muse Wonder against whoever you pick.

Choose a rival. Every counted test both have taken appears side by side as a share of the best published result on that test, with the category means above. A win is a higher share; a gap under 2 points is a tie, because one item on a 45-problem exam is 2.2 points and publishers' own standard errors are of that order.

Muse Wonder

#15·Index 71.5B-

2 : 12

wins · 2 ties · 16 shared

GPT-6 Astra

#1·Index 93.7A

GPT-6 Astra comes out ahead on 12 of the 16 tests both have taken.

Category means

Reasoning
65.2
96.1
Knowledge
—
80.4
Coding
69.6
93.4
Math
85.1
98.8
Agentic
65.7
90.6
Multimodal
60.8
89.6
Human preference
95.7
85.2

Shared tests · biggest gaps first

WeirdML v3Coding
24.9%
54.0%
−53.9
EBR-benchAgentic
31.4%
76.2%
−49.5
Furniture AssemblyMultimodal
54.2%
80.0%
−43.0
Mystery Game PuzzlesReasoning
51.0%
84.0%
−40.9
Blueprint-Bench 2Multimodal
31.7%
49.7%
−30.7
Code Arena (WebDev)Coding
1,650
1,767
−30.3
FrontierMath Tier 4Math
70.7%
97.6%
−26.9
ProofBenchMath
84.0%
99.0%
−15.0
Vending-Bench 2Agentic
$9,432
$15,515
−14.3
FrontierMath (Tiers 1–3)Math
82.1%
93.7%
−12.2
Text ArenaHuman preference
1,511
1,474
+10.5
GDP.pdfMultimodal
30.8%
34.2%
−9.7
CritPtReasoning
28.3%
31.7%
−9.5
SciCodeCoding
60.3%
56.5%
+5.7
APEX-AgentsAgentic
66.1%
64.7%
tie
Mock AIME 2024–2025Math
99.4%
100.0%
tie

Bars are distances to the best published result on each test (percent scores above chance, Arena ratings as win rate against the leader, open-ended values on a log scale). Raw values as the publishers report them.

Open GPT-6 Astra

Scores

Every test, every source

The best published run per benchmark, the raw value as the publisher reports it, who produced the number, how close it comes to the best published result on that test, and where the model sits among every model scored on it. Percent scores are read above chance, Arena ratings as a win rate against the board leader, open-ended values on a log scale. A test with too few models to compare against is shown but not counted, and so is an archived test: one whose publisher no longer covers new models.

Category means

Reasoning65.2 · 2/8
Knowledge—
Coding69.6 · 4/6
Math85.1 · 4/4
Agentic65.7 · 3/6
Multimodal60.8 · 3/4
Human preferencebeside95.7 · 1/1
Long context—

Mean · tests taken of the category's comparable tests. A faded category either rests on fewer than half of them or is a single-test category (marked “beside”), which is shown next to the Index and never averaged into it.

CritPtLeaderboardReasoning

28.3%

78.6% of the best (36.0%)
87th percentile of 102

max

Muse Wonder

Muse Wonder, in 17 results.

What Muse Wonder was asked to do, and how it did.

Muse Wonder against whoever you pick.

Every test, every source

Compare with its neighbours.

The best models, ranked here, working inside Theo.