OpenAIUnited States· released Sep 2026
Ranked #13, 24.6% behind the frontier on average.
OpenAI, United States. One of 30 models from this lab on the Index.
Snapshot November 10, 2026
OpenCharts Index
75.4
Ranked #13 (11 to 13) of 80 · 24.6% behind the frontier on average · 24 comparable tests · 5 counting categories
Drop any single test and the Index lands between 73.1 and 77.7, anywhere from #11 to #13. Neighbours inside that range are ties.
Needs more results (3 of 5 so far)
Averaging 92.9 on the 3 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 (91.9) and reasoning (83.5). It holds the best published result on Mock AIME 2024–2025. It trails the frontier most in agentic, 38.3% behind on average. Between 20% and 25% behind the best published results, on average. Drop any single test and it would sit anywhere from #11 to #13.
Strongest category
Math
Competition and research mathematics, graded on the final answer or the proof.
91.9
Mean of 4 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
Win a run of a deck-building strategy game at its hardest setting, playing from screenshots with a mouse and a keyboard.
9.2%
73.0% behind the best published result (34.0%) · #5 of 9.
It tests using a computer the way a person does, and decisions whose cost only shows up much later.
Not measured yet
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 91.9 across 4 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Source: Epoch AI (internal runs)Solve unpublished research-level mathematics problems written by professional mathematicians (tiers 1 to 3).
89.8%
94.5% of the best (95.1%)
#7 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.
90.0%
90.0% of the best (100.0%)
#7 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)Write a complete, rigorous proof, graded for rigor rather than for a final answer.
83.0%
83.0% of the best (100.0%)
#14 of 81
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 Sol
#13·Index 75.4B
0 : 22
wins · 2 ties · 24 shared
GPT-6 Astra
#1·Index 93.7A
GPT-6 Astra comes out ahead on 22 of the 24 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 Hub89.6%
94.3% of the best (95.0%)
88th percentile of 67 · n = 120
max
Source: Epoch AI — AI Benchmarking Hub95.5%
97.0% of the best (98.5%)
74th percentile of 67 · n = 100
max
Source: Epoch AI — AI Benchmarking Hub30.9%
85.7% of the best (36.0%)
93th percentile of 102
max
Source: Epoch AI — AI Benchmarking Hub56.0%
68.9% of the best (79.0%), above chance
81th percentile of 76 · n = 100
max
Source: Epoch AI — AI Benchmarking Hub56.0%
57.9% of the best (90.0%), above chance
85th percentile of 72 · n = 100
max
Source: Epoch AI — AI Benchmarking Hub60.7%
64.6% of the best (94.0%)
78th percentile of 75 · n = 1,000
max
Source: Epoch AI — AI Benchmarking Hub57.6%
86.2% of the best (66.9%)
80th percentile of 96 · n = 338
max
Source: Epoch AI — AI Benchmarking Hub27.6%
51.0% of the best (54.0%)
63th percentile of 25 · n = 11
xhigh · agent: codex_cli · reasoning effort: xhigh
Source: Epoch AI — AI Benchmarking Hub49.3%
90.2% of the best (54.6%)
83th percentile of 41
max · harness: codex · reasoning effort: max
Source: Epoch AI — AI Benchmarking Hub1,674
30% expected win rate against the board leader (1,818)
90th 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 Hub89.8%
94.5% of the best (95.1%)
92th percentile of 78 · n = 290
max
Source: Epoch AI — AI Benchmarking Hub90.0%
90.0% of the best (100.0%)
91th percentile of 68 · n = 48
max
Source: Epoch AI — AI Benchmarking Hub83.0%
83.0% of the best (100.0%)
83th percentile of 81
54.3%
64.5% of the best (84.2%)
54th percentile of 58
max
Source: Epoch AI — AI Benchmarking Hub$14,428
96.2% of the best ($16,484) on a log scale
97th percentile of 65
53.3%
58.9% of the best (90.5%)
76th percentile of 30 · n = 21
max
Source: Epoch AI — AI Benchmarking Hub9.2%
27.0% of the best (34.0%)
50th percentile of 9
max
Source: Epoch AI — AI Benchmarking Hub1,258
43% expected win rate against the board leader (1,309)
47th percentile of 71
max · board 2026-11-09
Source: Arena (LMArena) — Leaderboard Dataset58.3%
47.2% of the best (90.0%), above chance
75th percentile of 37 · n = 60
max
Source: Epoch AI — AI Benchmarking Hub36.9%
63.0% of the best (58.6%)
71th percentile of 36 · n = 50
26.4%
75.4% of the best (35.0%)
72th percentile of 37 · n = 100
max
Source: Epoch AI — AI Benchmarking Hub1,457
40% expected win rate against the board leader (1,526)
54th percentile of 113
max · board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetNearby 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.