SciCodeLeaderboard
Write research-grade scientific code, one sub-problem at a time, that passes unit tests.
38.5%
57.6% of the best (66.9%)
#86 of 96 · n = 338
Inception LabsUnited States· released Sep 2026
Mercury 2.5
Provisional: 3 comparable tests so far. Ranked once it reaches 6 across 2 counting categories.
Inception Labs, United States. One of 1 model from this lab on the Index.
Third-party publishedLow confidence (thin coverage)
Snapshot November 10, 2026
OpenCharts Index
20.2
Provisional: not enough comparable tests or counting categories to rank yet · 3 comparable tests · 0 counting categories
Drop any single test and the Index lands between 1.5 and 30.3.
Needs more results (0 of 5 so far)
Distance to today's frontier on the hardest tests. Not a measure of intelligence.
What it's known for
Mercury 2.5, in 3 results.
Its widest gap is on CritPt, 100.0% behind the best published result. No comparable results yet in knowledge, agentic, multimodal and human preference. Below 40% of the best published results, on average.
Strongest category
No category counts yet: a category counts once it has more than one comparable test and the model has taken at least half of them. The scores it has are below.
Best single result
SciCode
Write research-grade scientific code, one sub-problem at a time, that passes unit tests.
38.5%
57.6% of the best (66.9%) · #86 of 96.
Scientific programming needs the math and the code to be right at the same time.
Where it trails
CritPt
Solve an unpublished research-level physics problem to a numeric or symbolic answer checked by an official server.
0.0%
100.0% behind the best published result (36.0%) · #95 of 102.
Research physics is far past textbook recall. Audits found that many of these problems were stated ambiguously, so a low score here says less than it seems to.
Not measured yet
No comparable result yet in these 4 categories. A blank is a blank, never a zero, and it does not lower the Index.
- Knowledge
- Agentic
- Multimodal
- Human preference
Covered, but not averaged into the Index:
- Reasoning1 of 8 tests · needs 4 · mean 0.0
- Coding1 of 6 tests · needs 3 · mean 57.6
- Math1 of 4 tests · needs 2 · mean 3.0
See it at work
What Mercury 2.5 was asked to do, and how it did.
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.
Coding · mean 57.6 across 1 comparable test · not counted toward the Index yet (fewer than half the category's tests)
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
Mercury 2.5 against whoever you pick.
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.
Mercury 2.5
provisional·Index 20.2F
0 : 3
wins · 0 ties · 3 shared
GPT-6 Astra
#1·Index 93.7A
GPT-6 Astra comes out ahead on 3 of the 3 tests both have taken.
Category means
Reasoning
0.096.1Knowledge
—80.4Coding
57.693.4Math
3.098.8Agentic
—90.6Multimodal
—89.6Human preference
—85.2
Shared tests · biggest gaps first
- ProofBenchMath−96.03.0%99.0%
- CritPtReasoning−88.10.0%31.7%
- SciCodeCoding−26.838.5%56.5%
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
Every test, every source
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
- Reasoning0.0 · 1/8
- Knowledge—
- Coding57.6 · 1/6
- Math3.0 · 1/4
- Agentic—
- Multimodal—
- Human preference—
- Long context—
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.
CritPtLeaderboardReasoning
0.0%
0.0% of the best (36.0%)
0th percentile of 102
SciCodeLeaderboardCoding
38.5%
57.6% of the best (66.9%)
11th percentile of 96 · n = 338
ProofBenchLeaderboardMath
3.0%
3.0% of the best (100.0%)
3th percentile of 81
Top of the leaderboard
Compare with its neighbours.
The best models, ranked here, working inside Theo.
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.