Overview
| Name | Frontier general-purpose LLMs |
|---|---|
| Full name | No separate expanded name |
| Ambiguous names (not auto-linked) | Claude, GPT, Gemini |
| Family | Category entry for general closed LLMs from Anthropic, OpenAI and Google as test subjects; not one model, no single first release
|
| Organization | Anthropic, OpenAI, Google DeepMind |
| Organization type | Big-tech lab |
| Country | United States, United Kingdom |
| Model class | General-purpose LLM |
| Domain | Text, LLMs & agents |
| First release | No sourced date† · new version Basis: No single first release for a family entry; earliest cited members c. 2024-05/06 (unverified) |
| Other milestones | No other milestone recorded. |
| Latest update | No sourced date† · successor Basis: Current models listed on the developer model page Developer page lists Fable 5.2, Opus 5.5, Sonnet 5.5 and Haiku 5.5 as current, with no release dates; OpenAI and Google dates unverified Note: The earlier 2026-11-09 was back-derived from a retirement floor, not a release date; the four floors differ, so not one release day source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Vendors keep releasing new models |
| Openness | Code: Closed Weights: Closed Proprietary models accessed through APIs |
| Benchmarks reported | 5 counted (board 2, self 2, retrospective 1, unconfirmed 1) |
| Wet-lab validation | None recorded |
| Unverified fields | † first_release, latest_update, family.members, benchmarks_reported[2], benchmarks_reported[5] |
| As of | 2026-11-16 |
What it does
This site treats general frontier LLMs such as Claude, GPT and Gemini as one category entry, recording how they fare on bio benchmarks such as LAB-Bench and BixBench. They are test subjects, not biology-specific models.
Benchmarks reported
Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 5 of 6 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 18 LAB-Bench / LABBench2 | Official leaderboard or results | LABBench2 | Board | LABBench2 official board entries; family entry. · evidence |
| 29 BixBench | Official leaderboard or results | BixBench3 | Board | Successor's official board; counted as one family cell · evidence |
| 14 PubMedQA | Developer report, official protocol | — | Self-reported | Gemini 3 figures self-reported in the MedGemma 1.5 report; earlier board entries (GPT-4, Claude 3) were self-submitted. †partly verified · evidence |
| 42 BioMysteryBench | Developer report, official protocol | — | Self-reported | The publisher runs the benchmark itself and reports scores; the cross-vendor board is run by a third party. · evidence |
| 02 ProteinGym | Retrospective dataset use | — | Third-party | Scores from a second-hand aggregator; the entry is a family, not one model †unverified · no source link |
| 23 BioASQ | Unconfirmed (not counted) | — | Unconfirmed source | The overview ranks submitted systems, not the underlying LLMs. †disputed · evidence |
Other evaluations (outside the 44)
None recorded.
Developers report: Source states no developer claim
Independent evidence: No independent evidence found. No independent evidence found
Training data
Group in Figure 7: Not disclosed.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Not disclosed | |
| b. Private or licensed data | Not disclosed | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: Anthropic (founded 2021, San Francisco), OpenAI (founded 2015-12), Google DeepMind (merged 2023-04, Alphabet)
- Funding: Anthropic announced a Series H on 2026-05-28 at a $965B post-money valuation; OpenAI funding figures conflict across reports
- Products and partnerships: No product or partnership found
- Related models: MedGemma / Med-Gemini, GPT-Rosalind, Co-Scientist, Claude protein-design study (general model + public tools)
Reading notes
- LAB-Bench and BixBench come from Edison, itself a competitor
- Scores shift with thinking and tool settings; not comparable across sources
Caveats
- Not a single model: first release and latest update only make sense per member
- OpenAI and Google model names and dates not verified from primary pages
Sources
- Official page platform.claude.com (company blog)
- Official page advances.edisonscientific.com (company blog)
- arXiv preprint 2604.09554 (preprint)
- Anthropic BioMysteryBench article (company blog)
Corrections
1 correction
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update.description | Claude Fable 5.2 released "alongside" Opus 5.5 etc., dated 2026-11-09 | No release date on the developer page; 2026-11-09 was back-derived from a retirement floor and the four models were not released on one day | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.