BlogLLM Benchmark Scores as Published, Side by Side
OpenAI preparedness biology Critical capability evaluations: Results as Published
Every result the catalog holds for OpenAI preparedness biology Critical capability evaluations: 9 models from 1 developer, read from 4 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area BiosecurityMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30
OpenAI Preparedness Framework biology evaluations at the Critical threshold: AAV capsid packaging, SHP2 mean R2, Coronavirus-ACE2 composite, and phage-plasmid co-evolution negative log-likelihood.
Not checked against a maintainer's page.
Coronavirus-ACE2 composite
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.4741 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.423 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.36 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.349 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.45 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.43 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Phage-plasmid co-evolution (negative log-likelihood)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 10.8229 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 12.946 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 10.7 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 12.95 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 12.58 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 11.35 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
SHP2 mean R2
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.3696 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.332 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.13 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.23 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.4 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.3 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
AAV Capsid Packaging (Spearman)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.5285 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.5282 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.534 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.528 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.529 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
DNA sequence design for transcription factor binding (pass@1)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 11.27% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@1 |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 13.7% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@1 |
| GPT-5.5OpenAI, released 2026-04-23 | 13.82% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@1 |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 16.5% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@1 |
| GPT-5.4OpenAI, released 2026-03-05 | 12.82% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@1 |
Hard-negative protein binding prediction (pass@4)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 0% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@4 |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 7.6% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@4 |
| GPT-5.5OpenAI, released 2026-04-23 | 1.5% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@4 |
| GPT-5.5 ProOpenAI, released 2026-04-23 | 0% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@4 |
| GPT-5.4OpenAI, released 2026-03-05 | 3.5% | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25 | Attempt budget: pass@4 |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.