Llama 4 Maverick vs GPT-5.6 Terra
Llama 4 Maverick and GPT-5.6 Terra measured on clinical diagnosis & differential, on the same veterinary examination items, run on VetEval's own infrastructure at fixed decoding settings and scored by a panel that never grades its own model.
GPT-5.6 Terra scores 4.8 points above Llama 4 Maverick on Clinical Diagnosis & Differential, but their confidence intervals overlap, on this evidence the two cannot be separated.
Llama 4 Maverick and GPT-5.6 Terra carry a confirmed safety cap, which limits the Index regardless of how the clinical categories scored.
| Measure | Llama 4 MaverickMeta · open weights | GPT-5.6 TerraOpenAI · proprietary |
|---|---|---|
| VetEval Index | 19.018.1–19.8 | 27.0, best in this row26.1–27.9 |
| Rank | 8–9shared rank | 1–3shared rank |
| Clinical Diagnosis & Differential | 79.575.2–83.8 | 84.3, best in this row80.2–88.3 |
| Pharmacology & Dosing | 60.054.2–65.7 | 78.2, best in this row72.9–83.4 |
| Species-Specific Knowledge | 60.253.0–67.5 | 70.5, best in this row63.3–77.7 |
| Triage & Emergency | 67.460.4–74.5 | 81.5, best in this row75.5–87.5 |
| Preventive / Public Health / Zoonoses | 69.161.1–77.2 | 71.8, best in this row63.4–80.2 |
| Communication & Professionalism | 72.562.5–82.5 | 81.4, best in this row72.3–90.5 |
| Safety gate | Capped×0.40 | Capped×0.40 |
| Cost per 1,000 items | $1.29, best in this rowlist price at run time | $4.99list price at run time |
| Median time per question | 26.9sexcluding retries | 3.0s, best in this rowexcluding retries |
| Weights | OpenMeta | ProprietaryOpenAI |
A shaded cell is the best value in its row, and the bar shows the score out of 100. The line under the Index and each category is the 95% confidence interval, where two intervals overlap, the ordering is not something this measurement establishes. Cost is list price at the time of the run and is not part of the Index.
What this comparison does not tell you
- These scores describe performance on veterinary examination items. They are not a certification, and no result here licenses a model for clinical use.
- The Index weights categories for a general caseload. Every per-category score is published above so you can weigh them for yours instead, or compare on a single category using the control above.
- Cost and latency are measured at run time and move separately from the scores. A model that is cheaper today may not be next month.
Related comparisons
- Llama 4 Maverick vs GLM 5.3 Flash
- Llama 4 Maverick vs Minimax M3
- Llama 4 Maverick vs Grok 4.6
- Llama 4 Maverick vs GLM 5.3
- Llama 4 Maverick vs Claude Sonnet 5
Llama 4 Maverick vs GPT-5.6 Terra by category
Scope. VetEval measures model performance on veterinary examination items. It is not clinical advice, and no result here licenses a model for clinical use.