Moonshot AIChina· released Jan 2026· open weights
Provisional: 19 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
Moonshot AI, China. One of 5 models from this lab on the Index.
Snapshot September 8, 2026
OpenCharts Index
52.1
Provisional: not enough comparable tests or counting categories to rank yet · 19 comparable tests · 2 counting categories
Drop any single test and the Index lands between 48.0 and 56.4.
4 of 8 hardest tests · share of the frontier
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
Strongest in coding (56.4) and reasoning (47.7). It trails the frontier most in reasoning, 52.3% behind on average. Between 40% and 50% behind the best published results, on average.
Strongest category
Coding
Writing, fixing and shipping real code, judged by tests or users.
56.4
Mean of 5 of the category's 7 comparable tests. Counts toward the Index.
Best single result
Solve competition mathematics problems that have a single exact integer answer.
92.2%
92.2% of the best (100.0%) · #33 of 78.
Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.
Where it trails
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
3.1%
90.3% behind the best published result (32.3%) · #50 of 78.
Research physics is far past textbook recall. Only a few models produce anything a physicist would accept.
Not measured yet
Covered, but not averaged into the Index:
See it at work
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.
Math · mean 92.2 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)
Solve competition mathematics problems that have a single exact integer answer.
92.2%
92.2% of the best (100.0%)
#33 of 78 · n = 45
45 problems: one problem is 2.2 points, so gaps of a few points are within noise.
Source: Epoch AI (internal runs)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
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.
Kimi K2.5
provisional·Index 52.1C-
0 : 10
wins · 0 ties · 10 shared
GPT-6 Astra
#1·Index 99.0A+
GPT-6 Astra comes out ahead on 10 of the 10 tests both have taken.
Category means
Reasoning
Knowledge
Coding
Math
Agentic
Multimodal
Human preference
Long context
Shared tests · biggest gaps first
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
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.
Category means
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.
87.6%
88.5% of the best (95.8%), above chance
45th percentile of 78 · n = 198
24.4%
52.4% of the best (46.5%)
29th percentile of 18 · n = 2,500
11.8%
12.4% of the best (95.0%)
22th percentile of 51 · n = 120
65.3%
66.3% of the best (98.5%)
24th percentile of 51 · n = 100
46.8%
57.1% of the best (81.9%)
11th percentile of 46
3.1%
9.7% of the best (32.3%)
32th percentile of 78
34.3%
45.4% of the best (75.6%)
32th percentile of 57 · n = 1,000
73.8%
88.4% of the best (83.5%)
36th percentile of 26 · n = 500
49.0%
78.9% of the best (62.0%)
57th percentile of 73 · n = 338
45.6%
49.1% of the best (92.9%)
22th percentile of 69
31.9%
43.5% of the best (73.4%)
0th percentile of 21
1,436
11% expected win rate against the board leader (1,797)
45th percentile of 86
thinking · board 2026-09-05
Source: Arena (LMArena) — Leaderboard Dataset92.2%
92.2% of the best (100.0%)
57th percentile of 78 · n = 45
43.2%
51.0% of the best (84.7%)
46th percentile of 40
agent: Terminus 2
Source: Epoch AI — AI Benchmarking Hub14.4%
30.4% of the best (47.4%)
27th percentile of 49
$1,198
28.1% of the best ($11,182) on a log scale
27th percentile of 53
1,250
41% expected win rate against the board leader (1,313)
38th percentile of 54
thinking · board 2026-08-27
Source: Arena (LMArena) — Leaderboard Dataset1,451
42% expected win rate against the board leader (1,507)
47th percentile of 92
thinking · board 2026-09-02
Source: Arena (LMArena) — Leaderboard Dataset78.1%
78.1% of the best (100.0%)
67th percentile of 7
Top of the leaderboard
28 of the models on this page run inside Theo today. Theo picks the right one for each step and always shows which engine answered.