Vision ArenaLeaderboard
Answer prompts that include an image; real users vote blind between two models' answers.
1,248
41% expected win rate against the board leader (1,309)
#46 of 71
board 2026-11-09
Source: ArenaXiaomiChina· released Sep 2026· open weights
MiMo V2.6 Flash
Provisional: 6 comparable tests so far. Ranked once it reaches 6 across 2 counting categories.
Xiaomi, China. One of 4 models from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot November 10, 2026
OpenCharts Index
64.2
Provisional: not enough comparable tests or counting categories to rank yet · 6 comparable tests · 0 counting categories
Drop any single test and the Index lands between 59.7 and 72.0.
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
MiMo V2.6 Flash, in 6 results.
Its widest gap is on CritPt, 66.7% behind the best published result. No comparable results yet in knowledge and agentic. Between 35% and 40% 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
Vision Arena
Answer prompts that include an image; real users vote blind between two models' answers.
1,248
41% expected win rate against the board leader (1,309) · #46 of 71.
Seeing is half of most real tasks: screenshots, documents, photos and charts.
Where it trails
CritPt
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
12.0%
66.7% behind the best published result (36.0%) · #51 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 2 categories. A blank is a blank, never a zero, and it does not lower the Index.
- Knowledge
- Agentic
Covered, but not averaged into the Index:
- Reasoning1 of 8 tests · needs 4 · mean 33.3
- Coding2 of 6 tests · needs 3 · mean 64.4
- Math1 of 4 tests · needs 2 · mean 63.0
- Multimodal1 of 4 tests · needs 2 · mean 82.5
- Human preferencesingle-test category, shown beside the Index · 77.9
See it at work
What MiMo V2.6 Flash 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.
Multimodal · mean 82.5 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)
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 V2.6 Flash 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 V2.6 Flash
provisional·Index 64.2C
0 : 6
wins · 0 ties · 6 shared
GPT-6 Astra
#1·Index 93.7A
GPT-6 Astra comes out ahead on 6 of the 6 tests both have taken.
Category means
Reasoning
33.396.1Knowledge
—80.4Coding
64.493.4Math
63.098.8Agentic
—90.6Multimodal
82.589.6Human preference
77.985.2
Shared tests · biggest gaps first
- CritPtReasoning−54.812.0%31.7%
- ProofBenchMath−36.063.0%99.0%
- Code Arena (WebDev)Coding−33.41,6371,767
- Vision ArenaMultimodal−10.01,2481,283
- SciCodeCoding−7.851.3%56.5%
- Text ArenaHuman preference−7.31,4481,474
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
- Reasoning33.3 · 1/8
- Knowledge—
- Coding64.4 · 2/6
- Math63.0 · 1/4
- Agentic—
- Multimodal82.5 · 1/4
- Human preferencebeside77.9 · 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
12.0%
33.3% of the best (36.0%)
50th percentile of 102
SciCodeLeaderboardCoding
51.3%
76.6% of the best (66.9%)
49th percentile of 96 · n = 338
Code Arena (WebDev)LeaderboardCoding
1,637
26% expected win rate against the board leader (1,818)
83th percentile of 110
board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetProofBenchLeaderboardMath
63.0%
63.0% of the best (100.0%)
74th percentile of 81
Vision ArenaLeaderboardMultimodal
1,248
41% expected win rate against the board leader (1,309)
36th percentile of 71
board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetText ArenaLeaderboardHuman preference
1,448
39% expected win rate against the board leader (1,526)
43th 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.