Text ArenaLeaderboard
Answer the same prompt as a rival model; real users vote blind on which answer they prefer.
1,346
28% expected win rate against the board leader (1,507)
#90 of 92
board 2026-09-02
Source: ArenaMiniMaxChina· released Oct 2025· open weights
MiniMax M2
Provisional: 4 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
MiniMax, China. One of 5 models from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot September 8, 2026
OpenCharts Index
28.3
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 14.2 and 37.2.
Needs more results (1 of 8 so far)
Averaging 35.4 on the 1 it has; the score opens at 4 of 8.
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
MiniMax M2, in 4 results.
Its widest gap is on Vending-Bench 2, 100.0% behind the best published result. No comparable results yet in reasoning, knowledge, math, multimodal and long context. 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.
1,346
28% expected win rate against the board leader (1,507) · #90 of 92.
Millions of blind votes on real prompts are the market's measure of what people prefer.
Where it trails
Vending-Bench 2
Run a simulated vending business for a year: ordering, pricing and cash flow. The score is the final balance.
$161
100.0% behind the best published result ($11,182) on a log scale · #44 of 53.
Long-horizon decisions whose consequences compound. It exposes models that drift or forget.
Not measured yet
No comparable result yet in these 5 categories. A blank is a blank, never a zero, and it does not lower the Index.
- Reasoning
- Knowledge
- Math
- Multimodal
- Long context
Covered, but not averaged into the Index:
- Coding1 of 7 tests · needs 4 · mean 10.7
- Agentic2 of 8 tests · needs 4 · mean 17.7
- Human preferencesingle-test category, shown beside the Index · 56.6
See it at work
What MiniMax M2 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 56.6 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
MiniMax M2 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.
MiniMax M2
provisional·Index 28.3F
0 : 3
wins · 0 ties · 3 shared
Claude Fable 5.1
#2·Index 97.0A+
Claude Fable 5.1 comes out ahead on 3 of the 3 tests both have taken.
Category means
Reasoning
—97.5Knowledge
—93.7Coding
10.797.0Math
—96.6Agentic
17.788.4Human preference
56.699.2
Shared tests · biggest gaps first
- Code Arena (WebDev)Coding−79.31,2981,762
- Vending-Bench 2Agentic−76.7$161$5,422
- Text ArenaHuman preference−42.61,3461,504
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 Claude Fable 5.1Scores
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
- Reasoning—
- Knowledge—
- Coding10.7 · 1/7
- Math—
- Agentic17.7 · 2/8
- Multimodal—
- Human preferencebeside56.6 · 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.
Code Arena (WebDev)LeaderboardCoding
1,298
5% expected win rate against the board leader (1,797)
12th percentile of 86
board 2026-09-05
Source: Arena (LMArena) — Leaderboard DatasetTerminal-BenchLeaderboardAgentic
30.0%
35.4% of the best (84.7%)
21th percentile of 40
agent: Terminus 2
Source: Epoch AI — AI Benchmarking HubVending-Bench 2LeaderboardAgentic
$161
0.0% of the best ($11,182) on a log scale
0th percentile of 53
Text ArenaLeaderboardHuman preference
1,346
28% expected win rate against the board leader (1,507)
2th 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.