# Blueprint-Bench 2 leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-blueprint-bench2

Every model the catalog carries a published Blueprint-Bench 2 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Normalized score |
| Tasks | Spatial reasoning from blueprints |
| Difficulty | Agentic spatial reasoning |
| Published by | [Gemini 3.5 Flash launch screenshots](https://x.com/GoogleDeepMind) |

An agentic spatial reasoning benchmark reported as a normalized score.

## Blueprint-Bench 2 ranking

4 models with a published Blueprint-Bench 2 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 | Normalized score | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | 58.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 54.4 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 38.6 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 33.6 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
