Skip to content
← All news

News2 min read

Biohub final#188 of 3,947, top 5%

In August an agent workflow sat 8th on the Biohub cell-tracking public leaderboard. The final private rank is 188th of 3,947, the top 4.76%: lower, but an official finish. Plus the Kaggle tally when only final ranks count.

On 15 August, one of our agent workflows on Kaggle was 8th of 2,378 on the public leaderboard of Biohub – Cell Tracking During Development. That was the top 0.34%. It was among the ongoing results we reported then, under a note that the numbers were still moving.

The competition has closed. The authenticated final private rank is 188th of 3,947, the top 4.76%. That is a genuine top-5% finish on a closed board. It is also 188th, not 8th.

Biohub · where the result sits, in top %
  1. 10.34% 8th of 2,378 · public board, 15 August
  2. 24.76% 188th of 3,947 · final private board
This positioninside the top 5%

We do not know how much of the gap is the private board reshuffling and how much is everything that happened after 15 August: 1,569 more teams entered, and the rest of the field kept improving.2,378 teams on 15 August, 3,947 at the close. The point stands either way.

A public rank in the middle of a competition is a weather report.

We said so in August, and this is what it looks like.

The other boards that closed ​

Four of the competitions that were open in August now have final private ranks. Drag the divider to see each board then and now.

Four boards, twiceDrag to compare
15 August · public
#Competition · place
1Biohub – Cell Tracking: 8 / 2,378 · top 0.34%
2PTCG AI Battle: 955 / 6,829 · top 14.0%
3CUHK-X Small Model: 31 / 199 · top 15.6%
4Hyperspectral Detection: 10 / 40 · top 25%
Final · private
#Competition · place
1Biohub – Cell Tracking: 188 / 3,947 · top 4.76%
2PTCG AI Battle: 654 / 6,807 · top 9.61%
3CUHK-X Small Model: 56 / 326 · top 17.2%
4Hyperspectral Detection: 77 / 309 · top 24.9%
Top % of the field · lower is better
Biohub – Cell Tracking8 / 2,378 → 188 / 3,947
0.34%
4.76%
PTCG AI Battle955 / 6,829 → 654 / 6,807
13.98%
9.61%
CUHK-X Small Model31 / 199 → 56 / 326
15.58%
17.18%
Hyperspectral Detection10 / 40 → 77 / 309
25.00%
24.92%
A shorter bar is a better place.

Biohub fell the furthest. PTCG AI Battle rose, and Hyperspectral Detection held its place in a field almost eight times larger. The boards still open moved too: Solar Filament Segmentation went from 7th of 296 in August to 149th of 872 today.

One more closed with a striking number we cannot yet count. Predicting Smartphone Addiction shows an account at 2nd of 3,531, but on the public board as of the snapshot. That account's final private rank has not been recorded. The best authenticated private rank we have there is 564th. Until the private rank is in, rank 2 is not a finish, and we do not report it as one.

The tally, counting only final ranks ​

The AgentKaggle Team Radar (snapshot 2026-10-05 09:18 UTC) tracks 39 completed competitions. Taking the best tracked result in each, 16 are in the top 5%. Most of those are not finishes.

Final private ranks

3

Student Health Risk (top 2.00%), ROGII Wellbore Geology (top 2.24%) and Biohub (top 4.76%).

Late estimates

12

Real scores placed against a frozen final board. Not ranks, medals or evidence of having competed.

Public rank at snapshot

1

The Smartphone Addiction result above, until its private rank is in.

The 16 completed competitions in the top 5%, by kind of rank
Predicting Student Health RiskFinal, private673,3552.00%
ROGII - Wellbore Geology PredictionFinal, private1376,1252.24%
Biohub - Cell Tracking During DevelopmentFinal, private1883,9474.76%
Predicting Smartphone AddictionPublic, at snapshot23,5310.06%
NeurIPS 2025 - Google Code Golf ChampionshipLate estimate11,1420.09%
Critical temperature of superconductorsLate estimate14940.20%
Helios Corn Futures Climate ChallengeLate estimate11530.65%
Electricity consumptionLate estimate11500.67%
CMI - Detect Behavior with Sensor DataLate estimate192,6570.72%
Hash Code Archive - Photo Slideshow OptimizationLate estimate1891.12%
Salary Prediction for Job PostingsLate estimate1831.20%
Hash Code Archive - Drone DeliveryLate estimate21301.54%
Hotel booking demandLate estimate74061.72%
Information Retrieval Agent 2025Late estimate82223.60%
Scintillation Detector Signal TypesLate estimate4984.08%
March Machine Learning Mania 2025Late estimate841,7274.86%

The audit's charts are drawn with a fixed list of 12 competitions left out, so a chart rendered from today's data shows 27, not 39. All 12 are outside the top 15%, so leaving them out flatters the picture. The counts above use all 39. Of the 13 competitions still open, 3 sit in the top 5% of their public boards today. One of those 3 is Spaceship Titanic, a getting-started practice competition.

The set of tracked accounts has also changed since August, with some added and some dropped. That is why we compare competitions one by one here, and do not compare August's totals with today's.

The audit · Team Radar · HMA

Read next

News78.2% MLE-bench medal rate in 6 hoursTwo coding agents taking turns over one workspace, each starting fresh, beat both of them working alone on 75 MLE-bench tasks: 78.2% any-medal against 72.4% and 68.0%, in the same six hours. Self-reported, and not on the official leaderboard.Read it NewsTwo Kaggle finishes in the top 3%Ten agent workflows on Kaggle, with every result sorted by what kind of rank it is. Two closed with official final ranks in the top 3%. Twelve more top-5% results are late-submission estimates, and six live public boards had us in the top 5% on 15 August.Read it News#1 on Lean-Eval v1 first solvesLean-Eval froze its first 128-problem release and moved everything older to an archive. On v1 our GPT-5.6 flow has the most first solves, 30, and is one behind the leader on total; on the archive it has 170 of 171.Read it