Text ArenaLeaderboard
Answer the same prompt as a rival model; real users vote blind on which answer they prefer.
1,425
36% expected win rate against the board leader (1,526)
#89 of 113
board 2026-11-09
Source: ArenaMetaUnited States· released Aug 2026· open weights
Muse Glimmer
Provisional: 4 comparable tests so far. Ranked once it reaches 6 across 2 counting categories.
Meta, United States. One of 7 models from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot November 10, 2026
OpenCharts Index
39.6
Provisional: not enough comparable tests or counting categories to rank yet · 4 comparable tests · 0 counting categories
Drop any single test and the Index lands between 23.6 and 55.9.
Needs more results (0 of 5 so far)
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
Muse Glimmer, in 4 results.
Its widest gap is on CritPt, 92.9% behind the best published result. No comparable results yet in knowledge, math, agentic and multimodal. Below 40% of the best published results, on average.
Strongest category
No category counts yet: a category counts once it has more than one comparable test and the model has taken at least half of them. The scores it has are below.
Best single result
Text Arena
Answer the same prompt as a rival model; real users vote blind on which answer they prefer.
1,425
36% expected win rate against the board leader (1,526) · #89 of 113.
Millions of blind votes on real prompts are the market's measure of what people prefer.
Where it trails
CritPt
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
2.6%
92.9% behind the best published result (36.0%) · #77 of 102.
Research physics is far past textbook recall. Audits found that many of these problems were stated ambiguously, so a low score here says less than it seems to.
Not measured yet
No comparable result yet in these 4 categories. A blank is a blank, never a zero, and it does not lower the Index.
- Knowledge
- Math
- Agentic
- Multimodal
Covered, but not averaged into the Index:
- Reasoning1 of 8 tests · needs 4 · mean 7.1
- Coding2 of 6 tests · needs 3 · mean 40.1
- Human preferencesingle-test category, shown beside the Index · 71.7
See it at work
What Muse Glimmer 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 71.7 across 1 comparable test · a single-test category, shown beside the Index and never averaged into it
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 Glimmer 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 Glimmer
provisional·Index 39.6F
0 : 4
wins · 0 ties · 4 shared
GPT-6 Astra
#1·Index 93.7A
GPT-6 Astra comes out ahead on 4 of the 4 tests both have taken.
Category means
Reasoning
7.196.1Knowledge
—80.4Coding
40.193.4Math
—98.8Agentic
—90.6Multimodal
—89.6Human preference
71.785.2
Shared tests · biggest gaps first
- CritPtReasoning−81.02.6%31.7%
- Code Arena (WebDev)Coding−72.51,3551,767
- SciCodeCoding−17.344.9%56.5%
- Text ArenaHuman preference−13.51,4251,474
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 AstraScores
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
- Reasoning7.1 · 1/8
- Knowledge—
- Coding40.1 · 2/6
- Math—
- Agentic—
- Multimodal—
- Human preferencebeside71.7 · 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
2.6%
7.1% of the best (36.0%)
25th percentile of 102
high
Source: Epoch AI — AI Benchmarking HubSciCodeLeaderboardCoding
44.9%
67.1% of the best (66.9%)
26th percentile of 96 · n = 338
high
Source: Epoch AI — AI Benchmarking HubCode Arena (WebDev)LeaderboardCoding
1,355
7% expected win rate against the board leader (1,818)
15th percentile of 110
board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetText ArenaLeaderboardHuman preference
1,425
36% expected win rate against the board leader (1,526)
21th percentile of 113
board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetTop of the leaderboard
Compare with its neighbours.
The best models, ranked here, working inside Theo.
29 of the models on this page run inside Theo today. Theo picks the right one for each step and always shows which engine answered.