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.
Coding benchmark
Every model the catalog carries a published LiveCodeBench v5 value for, ranked by that value.
LiveCodeBench v5 is a named release and date-window slice. BenchLM keeps explicitly labeled v5 rows outside the rolling weighted lane. 9 models in the ModelScale catalog have a published value.
Each point is a model with a published LiveCodeBench v5 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
9 models with a published LiveCodeBench v5 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 | Provider-published v5 competitive programming result |
|---|---|---|---|
| 1 | InclusionAI | 82.8 | |
| 2 | Alibaba | 70.7 | |
| 3 | Alibaba | 65.7 |
What the benchmark measures and how its value is published, from the source’s own record.
LiveCodeBench v5 is a coding benchmark published by LiveCodeBench official repository and release documentation. LiveCodeBench v5 is a named release and date-window slice. BenchLM keeps explicitly labeled v5 rows outside the rolling weighted lane. Its evaluation set is described by the source as july 2024 to May 2025 release window. The source rates its difficulty as competitive programming level.
Each model's result is published by LiveCodeBench official repository and release documentation as provider-published v5 competitive programming result. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 9 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 | NVIDIA | 63.2 |
| 5 | Alibaba | 62.7 |
| 6 | Mistral | 59.4 |
| 7 | Mistral | 55.8 |
| 8 | Alibaba | 35.3 |
| 9 | Alibaba | 31.3 |
Evidence key: Observed
Rows are ordered by the value LiveCodeBench official repository and release documentation 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.