METR Q4 2026 TH2 - AZsPCs Powerful Sums (Human Percentile): leaderboard

METR's Q4 2026 capability update (20 November 2026): where a model's best 48-hour run on the past Al Zimmermann's Programming Contest "Powerful Sums" ranks among that contest's 233 human entrants, who had about three months. 100 means beating every human entrant. One of the 15 contests in the TH2 suite.

Metric: Percentile Among Human Participants. Source: metr.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 5.597.42#9
2Claude Fable 5.195.71#20
3GPT-6 Astra94.85#10
4GPT-6 Luna92.7#105
5Claude Opus 4.769.53#85
6Claude Haiku 5.566.95#75
7GPT-5.459.66#135
8Claude Opus 4.542.49#160
9GPT-532.62#178

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=metr-q4-2026-th2-azspcs-powerful-sums-human-percentile · How It Works · Data refreshed daily, snapshot 2026-11-21.