GoogleUnited States· released Oct 2026
Best published result on 5 of the 8 tests it has taken.
A preview that publishers score from early access. It is not generally available yet.
Snapshot November 10, 2026
OpenCharts Index
95.8
Provisional: not enough comparable tests or counting categories to rank yet · 8 comparable tests · 1 counting categories
Drop any single test and the Index lands between 95.8 and 98.2.
Needs more results (1 of 5 so far)
Averaging 87.5 on the 1 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 agentic (95.8). It holds the best published result on APEX-Agents, Blueprint-Bench 2 and CritPt and 2 more. Its widest gap is on Code Arena (WebDev), 14.2% behind the best published result. No comparable results yet in knowledge and math. Within 5% of the best published results, on average.
Strongest category
Agentic
Long-horizon tasks with tools: terminals, desktops, browsers, whole jobs.
95.8
Mean of 3 of the category's 6 comparable tests. Counts toward the Index.
Best single result
Complete professional-services work in consulting, law and finance as an agent, graded against expert rubrics.
84.2%
Best published result of 58 models.
Expert-graded knowledge work is what professional teams would actually delegate.
Where it trails
Build a web app from the same prompt as a rival model; real users vote blind on the result.
1,768
14.2 points short of parity with the board leader (1,818) · #3 of 110.
People judging finished apps side by side is the most honest measure of front-end quality.
Not measured yet
No comparable result yet in these 2 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 100.0 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
36.0%
best published result
of 102 models
high
Epoch AI's review rated version 1 Flawed (October 2026): two audits found scoring defects in at least a fifth of its problems. The leaderboard moved to a revised version 2 on October 22, 2026, and Epoch AI's file does not say which version each score comes from.
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 4 Carbon
provisional·Index 95.8A+
5 : 1
wins · 2 ties · 8 shared
GPT-6 Astra
#1·Index 93.7A
Gemini 4 Carbon comes out ahead on 5 of the 8 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.
36.0%
best published result
of 102 models
high
Source: Epoch AI — AI Benchmarking Hub64.2%
96.0% of the best (66.9%)
99th percentile of 96 · n = 338
high
Source: Epoch AI — AI Benchmarking Hub1,768
43% expected win rate against the board leader (1,818)
98th percentile of 110
high · board 2026-11-09
Source: Arena (LMArena) — Leaderboard Dataset84.2%
best published result
of 58 models
$16,484
best published result
of 65 models
61.2%
87.5% of the best (69.9%)
81th percentile of 22 · n = 34
high · harness: proximus
Source: Proximal (FrontierSWE leaderboard)58.6%
best published result
of 36 models
1,526
best published result
of 113 models
high · board 2026-11-09
Source: Arena (LMArena) — Leaderboard DatasetTop of 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.