OpenAIUnited States· released Oct 2026
Ranked #7, tested so far in 4 of the 5 categories the Index averages.
OpenAI, United States. One of 30 models from this lab on the Index.
Snapshot November 10, 2026
OpenCharts Index
82.2
Ranked #7 (5 to 9) of 80 · 17.8% behind the frontier on average · 16 comparable tests · 4 counting categories
Part of this Index is an estimate. On the 4 categories it is tested in, it averages 81.3. The rest is filled in from models tested in every category, because it has too few results to count there yet: Reasoning. Such estimates have been within 2.6 points about nine times in ten.
Its band runs from 79.6 to 85.4: where the Index could land once it is tested in every category, or if any single test were dropped. That covers #5 to #9, and neighbours inside that range are ties.
Needs more results (2 of 5 so far)
Averaging 94.2 on the 2 it has; the score opens at 4 of 5.
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
Strongest in math (96.1) and agentic (79.0). It holds the best published result on Mock AIME 2024–2025. It trails the frontier most in coding, 26.9% behind on average. No comparable result yet in human preference. Between 15% and 20% behind the best published results, on average. Part of its Index is an estimate. It has too few results in reasoning for that category to count, so it is filled in from models tested in every category. On the categories that do count it averages 81.3. Across its band it could sit anywhere from #5 to #9.
Strongest category
Math
Competition and research mathematics, graded on the final answer or the proof.
96.1
Mean of 3 of the category's 4 comparable tests. Counts toward the Index.
Best single result
Solve competition mathematics problems that have a single exact integer answer.
100.0%
Best published result of 98 models.
Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.
Where it trails
Answer a short factual question exactly, without searching, or say you do not know.
57.3%
39.0% behind the best published result (94.0%) · #21 of 75.
How often a model is right about facts, and how rarely it invents one, decides whether you can trust it unsupervised.
Not measured yet
No comparable result yet in this category. 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.
Math · mean 96.1 across 3 comparable tests · counts toward the Index
Solve competition mathematics problems that have a single exact integer answer.
100.0%
best published result
of 98 models
max
45 problems: one problem is 2.2 points, so gaps of a few points are within noise.
Source: Epoch AI (internal runs)Solve unpublished research-level mathematics problems written by professional mathematicians (tiers 1 to 3).
90.9%
95.6% of the best (95.1%)
#5 of 78 · n = 290
max
Commissioned by OpenAI, which has access to much of the problem set; Epoch discloses this and keeps a holdout it does not share.
Source: Epoch AI (internal runs)Solve the hardest FrontierMath tier: problems that take expert mathematicians days.
92.7%
92.7% of the best (100.0%)
#5 of 68 · n = 48
max
48 problems: one problem is about 2 points. Same OpenAI commissioning disclosure as tiers 1 to 3.
Source: Epoch AI (internal runs)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
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-6.1 Terra
#7·Index 82.2B+
2 : 12
wins · 2 ties · 16 shared
GPT-6 Astra
#1·Index 93.7A
GPT-6 Astra comes out ahead on 12 of the 16 tests both have taken.
Category means
Reasoning
Knowledge
Coding
Math
Agentic
Multimodal
Human preference
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, and so is an archived test: one whose publisher no longer covers new models.
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.
94.3%
97.1% of the best (96.4%), above chance
91th percentile of 96 · n = 198
max
Source: Epoch AI — AI Benchmarking Hub28.0%
77.8% of the best (36.0%)
86th percentile of 102
max
Source: Epoch AI — AI Benchmarking Hub74.0%
80.2% of the best (90.0%), above chance
96th percentile of 72 · n = 100
max
Source: Epoch AI — AI Benchmarking Hub57.3%
61.0% of the best (94.0%)
73th percentile of 75 · n = 1,000
max
Source: Epoch AI — AI Benchmarking Hub55.1%
82.4% of the best (66.9%)
69th percentile of 96 · n = 338
max
Source: Epoch AI — AI Benchmarking Hub40.4%
74.8% of the best (54.0%)
79th percentile of 25 · n = 11
xhigh · agent: codex_cli · reasoning effort: xhigh
Source: Epoch AI — AI Benchmarking Hub1,679
31% expected win rate against the board leader (1,818)
92th percentile of 110
max · board 2026-11-09
Source: Arena (LMArena) — Leaderboard Dataset100.0%
best published result
of 98 models
max
Source: Epoch AI — AI Benchmarking Hub90.9%
95.6% of the best (95.1%)
95th percentile of 78 · n = 290
max
Source: Epoch AI — AI Benchmarking Hub92.7%
92.7% of the best (100.0%)
94th percentile of 68 · n = 48
max
Source: Epoch AI — AI Benchmarking Hub68.3%
81.1% of the best (84.2%)
89th percentile of 58
max
Source: Epoch AI — AI Benchmarking Hub$9,107
83.0% of the best ($16,484) on a log scale
81th percentile of 65
78.1%
86.3% of the best (90.5%)
97th percentile of 30 · n = 21
max
Source: Epoch AI — AI Benchmarking Hub22.3%
65.7% of the best (34.0%)
75th percentile of 9
max
Source: Epoch AI — AI Benchmarking Hub79.2%
81.9% of the best (90.0%), above chance
89th percentile of 37 · n = 60
max
Source: Epoch AI — AI Benchmarking Hub42.1%
71.9% of the best (58.6%)
86th percentile of 36 · n = 50
Nearby on the leaderboard
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.