xAIUnited States· released Aug 2026
Ranked #13, 24.8% behind the frontier on average.
xAI, United States. One of 8 models from this lab on the Index.
Snapshot September 8, 2026
OpenCharts Index
75.2
Ranked #13 (10 to 16) of 36 · 24.8% behind the frontier on average · 17 comparable tests · 3 counting categories
Drop any single test and the Index lands between 71.2 and 78.6, anywhere from #10 to #16. Neighbours inside that range are ties.
Needs more results (3 of 8 so far)
Averaging 57.8 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 (82.1) and coding (80.2). It trails the frontier most in math, 36.7% behind on average. No comparable results yet in multimodal, human preference and long context. Between 20% and 25% behind the best published results, on average. Drop any single test and it would sit anywhere from #10 to #16.
Strongest category
Reasoning
Hard, novel problems: graduate science, abstract puzzles, expert exams.
82.1
Mean of 5 of the category's 6 comparable tests. Counts toward the Index.
Best single result
Solve competition mathematics problems that have a single exact integer answer.
99.2%
99.2% of the best (100.0%) · #7 of 78.
Olympiad-style problems need long, careful chains of reasoning, and there is no partial credit.
Where it trails
Solve the hardest FrontierMath tier: problems that take expert mathematicians days.
31.7%
67.5% behind the best published result (97.6%) · #19 of 51.
The deepest end of the set. Progress here signals genuinely new capability.
Not measured yet
No comparable result yet in these 3 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.
Agentic · mean 90.1 across 2 comparable tests · not counted toward the Index yet (fewer than half the category's tests)
Run a simulated vending business for a year: ordering, pricing and cash flow. The score is the final balance.
$9,047
93.2% of the best ($11,182) on a log scale
#4 of 53
Andon Labs estimates a strong human operator at roughly $63,000, so every model is far from the ceiling.
Source: Andon LabsComplete professional-services work in consulting, law and finance as an agent, graded against expert rubrics.
41.2%
86.9% of the best (47.4%)
#7 of 49
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.
Grok 4.6
#13·Index 75.2B
0 : 13
wins · 1 tie · 14 shared
GPT-6 Astra
#1·Index 99.0A+
GPT-6 Astra comes out ahead on 13 of the 14 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.
94.0%
97.5% of the best (95.8%), above chance
94th percentile of 78 · n = 198
high
Source: Epoch AI — AI Benchmarking Hub67.1%
70.6% of the best (95.0%)
66th percentile of 51 · n = 120
xhigh
Source: Epoch AI — AI Benchmarking Hub87.5%
88.8% of the best (98.5%)
52th percentile of 51 · n = 100
medium
Source: Epoch AI — AI Benchmarking Hub75.9%
92.7% of the best (81.9%)
87th percentile of 46
19.7%
61.0% of the best (32.3%)
79th percentile of 78
xhigh
Source: Epoch AI — AI Benchmarking Hub49.3%
65.2% of the best (75.6%)
64th percentile of 57 · n = 1,000
high
Source: Epoch AI — AI Benchmarking Hub54.6%
88.1% of the best (62.0%)
82th percentile of 73 · n = 338
medium
Source: Epoch AI — AI Benchmarking Hub67.3%
72.4% of the best (92.9%)
71th percentile of 69
high
Source: Epoch AI — AI Benchmarking Hub48.0%
89.8% of the best (53.5%)
85th percentile of 27
harness: grok-build · reasoning effort: high
Source: Epoch AI — AI Benchmarking Hub70.8%
96.5% of the best (73.4%)
95th percentile of 21
xhigh · reasoning level: Extra High
Source: Epoch AI — AI Benchmarking Hub1,625
27% expected win rate against the board leader (1,797)
92th percentile of 86
high · board 2026-09-05
Source: Arena (LMArena) — Leaderboard Dataset99.2%
99.2% of the best (100.0%)
92th percentile of 78 · n = 45
xhigh
Source: Epoch AI — AI Benchmarking Hub66.0%
70.4% of the best (93.7%)
67th percentile of 61 · n = 290
xhigh
Source: Epoch AI — AI Benchmarking Hub31.7%
32.5% of the best (97.6%)
60th percentile of 51 · n = 48
xhigh
Source: Epoch AI — AI Benchmarking Hub51.0%
51.0% of the best (100.0%)
75th percentile of 61
41.2%
86.9% of the best (47.4%)
88th percentile of 49
$9,047
93.2% of the best ($11,182) on a log scale
94th percentile of 53
Nearby on 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.