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.
Reasoning benchmark
Every model the catalog carries a published MRCRv2 value for, ranked by that value.
A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts. 14 models in the ModelChoice catalog have a published value.
Each point is a model with a published MRCRv2 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
14 models with a published MRCRv2 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 | Multi-round long-context evaluation |
|---|---|---|---|
| 1 | SASakana Fugu-Ultra | Sakana AI | 93.6 |
| 2 | Alibaba | 92.9 | |
| 3 | Alibaba | 91.7 | |
What the benchmark measures and how its value is published, from the source’s own record.
MRCRv2 is a reasoning benchmark published by Introducing GPT-5.2 and GPT-5.2 Pro. A long-context benchmark for memory, retrieval, and multi-round coherence over large contexts. Its evaluation set is described by the source as long-context retrieval. The source rates its difficulty as hard long-context.
Each model's result is published by Introducing GPT-5.2 and GPT-5.2 Pro as multi-round long-context evaluation. ModelChoice prints that value exactly as published, and never converts or rescales it. This page ranks the 14 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 |
| Alibaba |
| 90.4 |
| 5 | SASakana Fugu | Sakana AI | 86.6 |
| 6 | 77.3 |
| 7 | Inception | 75.5 |
| 8 | 72.2 |
| 9 | 66.4 |
| 10 | PAPokee-Isaac 28B | Pokee AI | 60.7 |
| 11 | 44.1 |
| 12 | 43.4 |
| 13 | 25.4 |
| 14 | 19.1 |
Evidence key: Observed
Rows are ordered by the value Introducing GPT-5.2 and GPT-5.2 Pro 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.