GoogleUnited States· released Feb 2026
Provisional: 3 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
Google, United States. One of 14 models from this lab on the Index.
Snapshot September 8, 2026
OpenCharts Index
88.7
Provisional: not enough comparable tests or counting categories to rank yet · 3 comparable tests · 1 counting categories
Drop any single test and the Index lands between 84.3 and 93.3.
Needs more results (1 of 8 so far)
Averaging 89.0 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
Strongest in reasoning (88.7). Its widest gap is on CritPt, 20.4% behind the best published result. No comparable results yet in knowledge, coding, math, agentic, multimodal, human preference and long context. Between 10% and 15% behind the best published results, on average.
Strongest category
Reasoning
Hard, novel problems: graduate science, abstract puzzles, expert exams.
88.7
Mean of 3 of the category's 6 comparable tests. Counts toward the Index.
Best single result
Solve the original Abstraction and Reasoning Corpus: small grids, a handful of examples, one hidden rule.
96.0%
97.5% of the best (98.5%) · #9 of 51.
The first ARC set is close to saturated at the frontier, so it now shows whether smaller models can generalize at all.
Where it trails
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
25.7%
20.4% behind the best published result (32.3%) · #10 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 7 categories. A blank is a blank, never a zero, and it does not lower 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.
Reasoning · mean 88.7 across 3 comparable tests · counts toward the Index
Solve the original Abstraction and Reasoning Corpus: small grids, a handful of examples, one hidden rule.
96.0%
97.5% of the best (98.5%)
#9 of 51 · n = 100
preview
Close to saturated at the frontier; scores depend on the compute budget a lab chose.
Source: ARC Prize FoundationInfer the hidden rule from a few input and output grid pairs, then apply it to a new grid.
84.6%
89.0% of the best (95.0%)
#7 of 51 · n = 120
preview
Scores depend on the compute budget a lab chose; ARC Prize publishes cost per task beside every score and this ranking does not.
Source: ARC Prize FoundationSolve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
25.7%
79.6% of the best (32.3%)
#10 of 78
preview
Source: CritPt / Artificial AnalysisEvery 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.
Gemini 3 Deep Think
provisional·Index 88.7A-
0 : 3
wins · 0 ties · 3 shared
GPT-6 Astra
#1·Index 99.0A+
GPT-6 Astra comes out ahead on 3 of the 3 tests both have taken.
Category means
Reasoning
Knowledge
Coding
Math
Agentic
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.
84.6%
89.0% of the best (95.0%)
84th percentile of 51 · n = 120
preview
Source: Epoch AI — AI Benchmarking Hub96.0%
97.5% of the best (98.5%)
84th percentile of 51 · n = 100
preview
Source: Epoch AI — AI Benchmarking Hub25.7%
79.6% of the best (32.3%)
88th percentile of 78
preview
Source: Epoch AI — AI Benchmarking HubTop 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.