Benchmark Facts
Top 6 of 20 models evaluated
| Model | Score 0–100 |
|---|---|
| 1 gpt-5.5 | 86.8±3.2 |
| 2 claude-opus-4-7 | 85.9±3.6 |
| 3 gpt-5.4 | 85.3±3.6 |
| 4 gemini-2.5-pro | 85.0±3.0 |
| 5 gpt-4o | 80.9±3.6 |
| 6 gemini-2.5-flash | 80.8±3.8 |
The benchmark of the Open Gastronomy Standard. Tasks put the OGS vocabularies and schemas in the prompt, so scores reflect reasoning with the standard rather than memorised trivia. Every task is scored deterministically and the aggregate is reported on a 0–100 scale.
Latest run per model, OGS-Bench v0.3. The leaderboard breaks every score down by category, language and task.
Top 6 of 20 models evaluated
| Model | Score 0–100 |
|---|---|
| 1 gpt-5.5 | 86.8±3.2 |
| 2 claude-opus-4-7 | 85.9±3.6 |
| 3 gpt-5.4 | 85.3±3.6 |
| 4 gemini-2.5-pro | 85.0±3.0 |
| 5 gpt-4o | 80.9±3.6 |
| 6 gemini-2.5-flash | 80.8±3.8 |
Category scores are means of their task scores; the aggregate weights them as set out in the specification.
| Category | Measures | Tasks |
|---|---|---|
regional | Cuisines, classic dishes, wine regions, grape varieties | 24 |
vocabulary | Knowledge of the OGS controlled vocabularies | 23 |
pairing | Choosing beverages for dishes | 22 |
sensory | Tastes, structure and aromatics on the 0–10 scale | 21 |
composition | Roles, cooking methods, Maillard index, reduction | 20 |
explanation | Choosing the right explanation codes | 20 |
risk | Spotting negative pairing interactions | 20 |
structured_output | Producing valid OGS JSON from a brief | 20 |
dietary | Dietary classifications and substitutions | 12 |
safety | Food-safety reasoning | 12 |
nutrition | Nutritional estimation | 10 |
menu_engineering | Menu balance, pricing and composition | 9 |
Each run is a single JSON document with the task-set fingerprint, configuration, exact prompts, raw responses and per-task scores. All runs are published as they are. When a scorer defect is found, the stored responses are re-scored and the correction is recorded in the document itself.
To have a model evaluated, contact opensource@gastrona.app.