Text ArenaLeaderboard
Answer the same prompt as a rival model; real users vote blind on which answer they prefer.
1,456
43% expected win rate against the board leader (1,507)
#43 of 92
board 2026-09-02
Source: ArenaByteDanceChina· released Mar 2026
Seed 2.0 Pro
Provisional: 2 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
ByteDance, China. One of 1 model from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot September 8, 2026
OpenCharts Index
84.7
Provisional: not enough comparable tests or counting categories to rank yet · 2 comparable tests · 0 counting categories
Drop any single test and the Index lands between 84.0 and 85.3.
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
Seed 2.0 Pro, in 2 results.
Its widest gap is on Vision Arena, 16.0% behind the best published result. No comparable results yet in reasoning, knowledge, coding, math, agentic and long context. Between 15% and 20% 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.
1,456
43% expected win rate against the board leader (1,507) · #43 of 92.
Millions of blind votes on real prompts are the market's measure of what people prefer.
Where it trails
Vision Arena
Answer prompts that include an image; real users vote blind between two models' answers.
1,257
16.0 points short of parity with the board leader (1,313) · #28 of 54.
Seeing is half of most real tasks: screenshots, documents, photos and charts.
Not measured yet
No comparable result yet in these 6 categories. A blank is a blank, never a zero, and it does not lower the Index.
- Reasoning
- Knowledge
- Coding
- Math
- Agentic
- Long context
Covered, but not averaged into the Index:
- Multimodalsingle-test category, shown beside the Index · 84.0
- Human preferencesingle-test category, shown beside the Index · 85.3
See it at work
What Seed 2.0 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 85.3 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.
Scores
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—
- Coding—
- Math—
- Agentic—
- Multimodalbeside84.0 · 1/1
- Human preferencebeside85.3 · 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.
Vision ArenaLeaderboardMultimodal
1,257
42% expected win rate against the board leader (1,313)
49th percentile of 54
board 2026-08-27
Source: Arena (LMArena) — Leaderboard DatasetText ArenaLeaderboardHuman preference
1,456
43% expected win rate against the board leader (1,507)
54th 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.