Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Mathematics benchmark
Harvard-MIT Mathematics Tournament November 2025. Every model the catalog carries a published HMMT Nov 2025 value for, ranked by that value.
A November 2025 HMMT slice for high-end mathematical reasoning comparisons. 12 models in the ModelChoice catalog have a published value.
Each point is a model with a published HMMT Nov 2025 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
12 models with a published HMMT Nov 2025 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Contest mathematics |
|---|---|---|---|
| 1 | Z.AI | 96.9 | |
| 2 | Alibaba | 94.6 | |
| 3 | Z.AI | 94.4 | |
What the benchmark measures and how its value is published, from the source’s own record.
HMMT Nov 2025 (Harvard-MIT Mathematics Tournament November 2025) is a mathematics benchmark published by Qwen3.6 launch benchmarks. A November 2025 HMMT slice for high-end mathematical reasoning comparisons. Its evaluation set is described by the source as competition math problems. The source rates its difficulty as olympiad-style mathematics.
Each model's result is published by Qwen3.6 launch benchmarks as contest mathematics. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 12 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 |
| Z.AI |
| 94.0 |
| 5 | Anthropic | 93.3 |
| 6 | Alibaba | 92.7 |
| 7 | Moonshot AI | 91.1 |
| 8 | Alibaba | 90.7 |
| 9 | Alibaba | 89.1 |
| 10 | SASarvam 105B | Sarvam | 85.8 |
| 11 | MiniMax | 81.0 |
| 12 | SASarvam 30B | Sarvam | 74.2 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.