VetEval
Sign in

Claude Sonnet 5 vs Minimax M3

Claude Sonnet 5 and Minimax M3 measured on pharmacology & dosing, 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.

Claude Sonnet 5 scores 5.2 points above Minimax M3 on Pharmacology & Dosing, but their confidence intervals overlap, on this evidence the two cannot be separated.

Claude Sonnet 5 and Minimax M3 carry a confirmed safety cap, which limits the Index regardless of how the clinical categories scored.

2 of 4 models. Press Compare to see the results.

Side-by-side comparison of Claude Sonnet 5, Minimax M3 across the VetEval Index, each scoring category, the safety gate, cost and latency.
MeasureClaude Sonnet 5Anthropic · proprietaryMinimax M3Minimax · open weights
VetEval Index22.3, best in this row21.4–23.118.117.4–18.9
Rank5–7shared rank8–9shared rank
Clinical Diagnosis & Differential73.268.1–78.277.4, best in this row73.1–81.8
Pharmacology & Dosing68.2, best in this row62.6–73.863.057.4–68.6
Species-Specific Knowledge62.0, best in this row54.6–69.456.349.3–63.3
Triage & Emergency76.6, best in this row70.1–83.066.258.9–73.4
Preventive / Public Health / Zoonoses57.748.4–67.074.3, best in this row67.0–81.5
Communication & Professionalism80.1, best in this row71.5–88.678.469.0–87.8
Safety gateCapped×0.40Capped×0.40
Cost per 1,000 items$2.48list price at run time$2.11, best in this rowlist price at run time
Median time per question1.6s, best in this rowexcluding retries4.2sexcluding retries
WeightsProprietaryAnthropicOpenMinimax

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

Claude Sonnet 5 vs Minimax M3 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.