# Furniture Assembly leaderboard

external 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://modelchoice.dev/leaderboards/benchmarks/external-furniture-assembly

Furniture Assembly Benchmark (Epoch AI). Every model the catalog carries a published Furniture Assembly value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agentic visual check with manual PDF, zoom tool and Python, 80-step budget |
| Tasks | 60 photos of three IKEA builds, some with deliberate assembly mistakes |
| Difficulty | Spatial reasoning from technical diagrams to real photos |
| Published by | [Furniture Assembly Benchmark (Epoch AI)](https://epoch.ai/benchmarks/furniture-assembly) |

Epoch AI's Furniture Assembly benchmark shows models photos of IKEA furniture builds with the official manual and asks whether the build is correct so far and, if not, which step went wrong.

## Furniture Assembly ranking

40 models with a published Furniture Assembly 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 | Agentic visual check with manual PDF, zoom tool and Python, 80-step budget | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://modelchoice.dev/models/claude-fable-5-2) | Anthropic | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Gemini 4 Neon](https://modelchoice.dev/models/gemini-4-neon) | Google | 89.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 89.2 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 83.3 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 80.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 80.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 4 Carbon](https://modelchoice.dev/models/gemini-4-carbon) | Google | 77.5 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Sonnet 5.5](https://modelchoice.dev/models/claude-sonnet-5-5) | Anthropic | 75.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Gemini 4 Argon](https://modelchoice.dev/models/gemini-4-argon) | Google | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Fable 5.1](https://modelchoice.dev/models/claude-fable-5-1) | Anthropic | 70.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 60.8 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 58.3 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Gemini 4 Hydrogen](https://modelchoice.dev/models/gemini-4-hydrogen) | Google | 57.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 56.7 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 55.8 | Observed 2026-11-21 · source benchlm:models |
| 17 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 54.2 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Muse Wonder](https://modelchoice.dev/models/muse-wonder) | Meta | 54.2 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Claude Haiku 5.5](https://modelchoice.dev/models/claude-haiku-5-5) | Anthropic | 47.5 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 44.2 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 44.2 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Claude Opus 4.8](https://modelchoice.dev/models/claude-opus-4-8) | Anthropic | 42.5 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 42.5 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Grok 4.6](https://modelchoice.dev/models/grok-4-6) | xAI | 40.0 | Observed 2026-11-21 · source benchlm:models |
| 25 | [GPT-5.2](https://modelchoice.dev/models/gpt-5-2) | OpenAI | 38.3 | Observed 2026-11-21 · source benchlm:models |
| 26 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 37.5 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Claude Fable 5](https://modelchoice.dev/models/claude-fable-5) | Anthropic | 35.8 | Observed 2026-11-21 · source benchlm:models |
| 28 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 34.2 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 34.2 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 33.3 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 31.7 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 28.3 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 28.3 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 26.7 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 26.7 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 23.3 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 22.5 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 21.7 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Grok 4.7](https://modelchoice.dev/models/grok-4-7) | xAI | 20.8 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Mistral Large 4](https://modelchoice.dev/models/mistral-large-4) | Mistral | 20.8 | 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.
