OpenAIUnited States· released Dec 2025
Provisional: 5 comparable tests so far. Ranked once it reaches 6 across 3 counting categories.
OpenAI, United States. One of 26 models from this lab on the Index.
Snapshot September 8, 2026
OpenCharts Index
73.0
Provisional: not enough comparable tests or counting categories to rank yet · 5 comparable tests · 1 counting categories
Drop any single test and the Index lands between 63.4 and 73.0.
Needs more results (3 of 8 so far)
Averaging 61.0 on the 3 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 (73.0). Its widest gap is on FrontierMath Tier 4, 52.9% behind the best published result. No comparable results yet in knowledge, coding, agentic, multimodal, human preference and long context. Between 25% and 30% behind the best published results, on average.
Strongest category
Reasoning
Hard, novel problems: graduate science, abstract puzzles, expert exams.
73.0
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.
90.5%
91.9% of the best (98.5%) · #20 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 the hardest FrontierMath tier: problems that take expert mathematicians days.
46.0%
52.9% behind the best published result (97.6%) · #15 of 51.
The deepest end of the set. Progress here signals genuinely new capability.
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.
Covered, but not averaged into 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 73.0 across 3 comparable tests · counts toward the Index
Solve the original Abstraction and Reasoning Corpus: small grids, a handful of examples, one hidden rule.
90.5%
91.9% of the best (98.5%)
#20 of 51 · n = 100
2025-12-11 · xhigh
Close to saturated at the frontier; scores depend on the compute budget a lab chose.
Source: ARC Prize FoundationAnswer everyday trick questions about the physical and social world that most people find easy.
57.4%
70.1% of the best (81.9%)
#29 of 46
2025-12-11
Source: SimpleBench / LM CouncilInfer the hidden rule from a few input and output grid pairs, then apply it to a new grid.
54.2%
57.0% of the best (95.0%)
#26 of 51 · n = 120
2025-12-11 · high
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 FoundationEvery 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.
GPT-5.2 Pro
provisional·Index 73.0B-
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
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.
54.2%
57.0% of the best (95.0%)
50th percentile of 51 · n = 120
2025-12-11 · high
Source: Epoch AI — AI Benchmarking Hub90.5%
91.9% of the best (98.5%)
60th percentile of 51 · n = 100
2025-12-11 · xhigh
Source: Epoch AI — AI Benchmarking Hub57.4%
70.1% of the best (81.9%)
38th percentile of 46
2025-12-11
Source: Epoch AI — AI Benchmarking Hub74.0%
79.0% of the best (93.7%)
78th percentile of 61 · n = 290
2025-12-11 · xhigh
Source: Epoch AI — AI Benchmarking Hub46.0%
47.1% of the best (97.6%)
72th percentile of 51 · n = 48
2025-12-11 · xhigh
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.