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 VulcanBench v3 value for, ranked by that value.
An open software-engineering benchmark built from real merged post-cutoff pull requests across Python, Rust, TypeScript, JavaScript, and Go repositories. Replaced by VulcanBench Frontier v4 in September 2026. 14 models in the ModelChoice catalog have a published value.
Each point is a model with a published VulcanBench v3 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 VulcanBench v3 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 | Pass@1 with low, medium, and high effort |
|---|---|---|---|
| 1 | xAI | 89.9 | |
| 2 | Anthropic | 89.5 | |
| 3 | DeepSeek | 88.4 |
What the benchmark measures and how its value is published, from the source’s own record.
VulcanBench v3 is a coding benchmark published by VulcanBench. An open software-engineering benchmark built from real merged post-cutoff pull requests across Python, Rust, TypeScript, JavaScript, and Go repositories. Replaced by VulcanBench Frontier v4 in September 2026. Its evaluation set is described by the source as 23 post-cutoff repository tasks in the v3 report. The source rates its difficulty as professional multi-file software engineering.
Each model's result is published by VulcanBench as pass@1 with low, medium, and high effort. ModelChoice prints that value to 1 decimal place, 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 | Anthropic | 87.0 |
| 4 | OpenAI | 87.0 |
| 4 | OpenAI | 87.0 |
| 4 | xAI | 87.0 |
| 4 | Meta | 87.0 |
| 9 | OpenAI | 85.5 |
| 10 | Alibaba | 82.6 |
| 11 | Alibaba | 81.2 |
| 12 | Z.AI | 78.3 |
| 13 | Anthropic | 76.2 |
| 14 | Moonshot AI | 73.7 |
Evidence key: Observed
Rows are ordered by the value VulcanBench 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.