BlogLLM Benchmark Scores as Published, Side by Side
SVG-Bench: Results as Published
Every result the catalog holds for SVG-Bench: 5 models from 4 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Code GenerationMaintainer MiniMaxIntroduced 2026Data version 2026103001, as of 2026-10-30
SVG-Bench is a MiniMax internal benchmark. The input is text or an image, and the task is to build an SVG from scratch or edit an existing asset. The work is done in a coding scaffold. A vision-language model checks whether the rendering is accurate, and the score is the average of three runs.
SVG-Bench (MiniMax internal)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.5OpenAI, released 2026-04-23 | 58.2% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 62.3% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 59.2% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| MiniMax M3MiniMax, released 2026-06-01 | 63.7% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| MiniMax M2.7MiniMax, released 2026-03-18 | 48% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.