Enter opens the highlighted result. Esc closes.

Phage--plasmid Co-evolution leaderboard

As of November 22, 2026, among the results listed here, OpenAI GPT-6 Astra has the highest reported Phage--plasmid Co-evolution score, 13.1 (Median of pair-weighted negative log-likelihood (lower is better)), published by OpenAI, ahead of OpenAI GPT-6.1 Sol at 12.9. 9 models have a Phage--plasmid Co-evolution result in our records.

Scores as the model makers published them, not re-run by us; each row links to its announcement.

Best reported score

13.1

OpenAI GPT-6 Astra

Reported by OpenAI, November 17, 2026 · Median of pair-weighted negative log-likelihood (lower is better)

Runner-up

12.9

OpenAI GPT-6.1 Sol

Reported by OpenAI, September 4, 2026 · Negative log-likelihood (lower is better)

9 models ranked · 1 maker

Reported Phage--plasmid Co-evolution scores

Phage--plasmid Co-evolution scores reported by model makers
Rank Model Score Setting Reported by Date
1 GPT-6 Astra 13.1 Median of pair-weighted negative log-likelihood (lower is better) OpenAI November 17, 2026 (model release)
2 GPT-6.1 Sol 12.9 Negative log-likelihood (lower is better) OpenAI September 4, 2026 (model release)
3 GPT-6 Sol 12.9 Negative log-likelihood (lower is better) OpenAI September 4, 2026 (model release)
4 GPT-6.2 Sol 12.4 Median of pair-weighted negative log-likelihood (lower is better) OpenAI November 17, 2026 (model release)
5 GPT-5.5 12 Median of pair-weighted negative log-likelihood (lower is better) OpenAI November 17, 2026 (model release)
6 GPT-6.2 Astra 11.6 Median of pair-weighted negative log-likelihood (lower is better) OpenAI November 17, 2026 (model release)
7 GPT-5.6 Sol 11.4 Negative log-likelihood (lower is better) OpenAI September 4, 2026 (model release)
8 GPT-6.1 Terra 10.8 Negative log-likelihood (lower is better) OpenAI October 26, 2026 (model release)
9 GPT-5 10.8 Median of pair-weighted negative log-likelihood (lower is better) OpenAI November 17, 2026 (model release)

Other reported runs

Phage--plasmid Co-evolution scores reported by model makers, other reported runs
Model Score Setting Reported by Date
GPT-6 Astra 12.6 Negative log-likelihood (lower is better) OpenAI September 4, 2026 (model release)

How much to trust these numbers

Source
Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
Settings
Settings differ between makers. Check the Setting column before comparing two scores.
Spread
13.1 to 10.8 across 9 models.
Freshness
Newest result published November 17, 2026; oldest September 4, 2026.

What Phage--plasmid Co-evolution measures

Phage--plasmid Co-evolution appears in the release announcements of OpenAI. We have not found a public write-up of the benchmark itself yet.