BlogLLM Benchmark Scores as Published, Side by Side
OpenAI preparedness biology High capability evaluations: Results as Published
Every result the catalog holds for OpenAI preparedness biology High capability evaluations: 6 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 High threshold: Multimodal Troubleshooting Virology, ProtocolQA Open-Ended (the existing protocolqa family), Tacit Knowledge and Troubleshooting, and TroubleshootingBench.
Not checked against a maintainer's page.
Multimodal Troubleshooting Virology
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 52.54% | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 55.34% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 49.1% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 51.68% | 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 | 63.11% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 55.5% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
TroubleshootingBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 SolOpenAI, released 2026-09-29 | 47.96% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 38.6% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 41.83% | 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 | 63.46% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 48% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
Tacit Knowledge and Troubleshooting
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 SolOpenAI, released 2026-09-29 | 88.5% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 69.2% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 72.45% | 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 | 92.55% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
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.