Text ArenaLeaderboard
Answer the same prompt as a rival model; real users vote blind on which answer they prefer.
1,468
44% expected win rate against the board leader (1,507)
#31 of 92
board 2026-09-02
Source: ArenaXiaomiChina· released May 2026· open weights
MiMo V2.5 Pro
Provisional: 5 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
Xiaomi, China. One of 2 models from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot September 8, 2026
OpenCharts Index
44.3
Provisional: not enough comparable tests or counting categories to rank yet · 5 comparable tests · 0 counting categories
Drop any single test and the Index lands between 29.5 and 55.0.
Needs more results (0 of 8 so far)
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
MiMo V2.5 Pro, in 5 results.
Its widest gap is on CritPt, 87.6% behind the best published result. No comparable results yet in knowledge, agentic, multimodal and long context. Between 50% and 60% behind 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.
1,468
44% expected win rate against the board leader (1,507) · #31 of 92.
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Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
4.0%
87.6% behind the best published result (32.3%) · #47 of 78.
Research physics is far past textbook recall. Only a few models produce anything a physicist would accept.
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
- Agentic
- Multimodal
- Long context
Covered, but not averaged into the Index:
- Reasoning1 of 6 tests · needs 3 · mean 12.4
- Coding2 of 7 tests · needs 4 · mean 54.1
- Math1 of 5 tests · needs 3 · mean 22.0
- Human preferencesingle-test category, shown beside the Index · 88.8
See it at work
What MiMo V2.5 Pro 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 88.8 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
MiMo V2.5 Pro 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.
MiMo V2.5 Pro
provisional·Index 44.3D
0 : 4
wins · 0 ties · 4 shared
GPT-6 Astra
#1·Index 99.0A+
GPT-6 Astra comes out ahead on 4 of the 4 tests both have taken.
Category means
Reasoning
12.499.6Knowledge
—100.0Coding
54.197.7Math
22.099.8Agentic
—98.5Human preference
88.8—
Shared tests · biggest gaps first
- CritPtReasoning−85.84.0%31.7%
- ProofBenchMath−77.022.0%99.0%
- Code Arena (WebDev)Coding−72.91,4751,797
- SciCodeCoding−10.050.2%56.5%
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.
Category means
- Reasoning12.4 · 1/6
- Knowledge—
- Coding54.1 · 2/7
- Math22.0 · 1/5
- Agentic—
- Multimodal—
- Human preferencebeside88.8 · 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
4.0%
12.4% of the best (32.3%)
40th percentile of 78
SciCodeLeaderboardCoding
50.2%
81.0% of the best (62.0%)
63th percentile of 73 · n = 338
Code Arena (WebDev)LeaderboardCoding
1,475
14% expected win rate against the board leader (1,797)
55th percentile of 86
board 2026-09-05
Source: Arena (LMArena) — Leaderboard DatasetProofBenchLeaderboardMath
22.0%
22.0% of the best (100.0%)
47th percentile of 61
Text ArenaLeaderboardHuman preference
1,468
44% expected win rate against the board leader (1,507)
66th percentile of 92
board 2026-09-02
Source: Arena (LMArena) — Leaderboard DatasetTop of the leaderboard
Compare with its neighbours.
The best models, ranked here, working inside Theo.
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.