SHP2 protein function leaderboard
As of November 22, 2026, among the results listed here, OpenAI GPT-6.2 Astra has the highest reported SHP2 protein function score, 0.5 (Mean of median R² across three assays (higher is better)), published by OpenAI, ahead of OpenAI GPT-6 Astra at 0.4. 5 models have a SHP2 protein function 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
0.5
Reported by OpenAI, November 17, 2026 · Mean of median R² across three assays (higher is better)
Runner-up
0.4
Reported by OpenAI, November 17, 2026 · Mean of median R² across three assays (higher is better)
5 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Astra | 0.5 | Mean of median R² across three assays (higher is better) | OpenAI | November 17, 2026 (model release) |
| 2 | GPT-6 Astra | 0.4 | Mean of median R² across three assays (higher is better) | OpenAI | November 17, 2026 (model release) |
| 3 | GPT-6.2 Sol | 0.4 | Mean of median R² across three assays (higher is better) | OpenAI | November 17, 2026 (model release) |
| 4 | GPT-5.5 | 0.2 | Mean of median R² across three assays (higher is better) | OpenAI | November 17, 2026 (model release) |
| 5 | GPT-5 | 0 | Mean of median R² across three assays (higher is better) | OpenAI | November 17, 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
- All ranked results use the same reported setting.
- Spread
- 0.5 to 0 across 5 models.
- Freshness
- Published November 17, 2026.
What SHP2 protein function measures
Models predict held-out SHP2 mutation assay outcomes across three unpublished datasets; mean R² indicates how well predictions explain variation in measured outcomes. Source: GPT-6.2 System Card - Deployment Safety Hub - OpenAI