Furniture assembly leaderboard
- Claude Opus 5.5 leads
- 83.3%
- models measured
- 33
- lead over #2
- +3.3 pts
- median
- 38.3%
Leader on Furniture assembly · read October 21
On October 21, 2026, 33 of our catalog's models had a Furniture assembly result, and Anthropic Claude Opus 5.5 led with 83.3%.
Epoch AI collects its results; its benchmarking hub describes the tasks and links the authors.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5Anthropic | 83.3% | 92.2 | $20.00 | |
| 2 | GPT-6 AstraOpenAI | 80.0% | 88.7 | $50.00 | |
| 3 | GPT-6.1 SolOpenAI | 80.0% | 88.7 | $10.00 | |
| 4 | Claude Sonnet 5.5Anthropic | 75.0% | 88.9 | $10.00 | |
| 5 | Gemini 4 ArgonGoogle | 72.5% | 80.5 | $10.00 | |
| 6 | Claude Fable 5.1Anthropic | 70.0% | 89.1 | $50.00 | |
| 7 | Claude Opus 5Anthropic | 60.8% | 81.8 | $25.00 | |
| 8 | GPT-6 SolOpenAI | 58.3% | 82.8 | $10.00 | |
| 9 | GPT-5.6 SolOpenAI | 56.7% | 76.7 | $20.00 | |
| 10 | GPT-5.6 TerraOpenAI | 54.2% | 69.0 | $12.00 | |
| 11 | Claude Haiku 5.5Anthropic | 47.5% | 75.9 | $0.50 | |
| 12 | GPT-5.5OpenAI | 44.2% | 67.8 | $30.00 | |
| 13 | GPT-6 LunaOpenAI | 44.2% | 71.4 | $0.50 | |
| 14 | Claude Opus 4.8Anthropic | 42.5% | 66.0 | $25.00 | |
| 15 | GPT-5.6 LunaOpenAI | 42.5% | 61.5 | $1.20 | |
| 16 | Grok 4.6xAI | 40.0% | 76.4 | $6.00 | |
| 17 | GPT-5.2OpenAI | 38.3% | 58.9 | $14.00 | |
| 18 | GPT-5.4OpenAI | 37.5% | 37.7 | $15.00 | |
| 19 | Claude Fable 5Anthropic | 35.8% | 82.1 | $50.00 | |
| 20 | DeepSeek V4.1 FlashDeepSeek | 34.2% | 77.2 | $0.525 | |
| 21 | Kimi K3Moonshot AI | 34.2% | 61.8 | $11.936 | |
| 22 | Claude Opus 4.7Anthropic | 33.3% | 51.1 | $25.00 | |
| 23 | Gemini 3.8 FlashGoogle | 31.7% | 70.5 | $4.125 | |
| 24 | Claude Opus 4.5Anthropic | 28.3% | 66.8 | $25.00 | |
| 25 | Claude Opus 4.6Anthropic | 28.3% | 66.9 | $25.00 | |
| 26 | Gemini 3.1 Pro PreviewGoogle | 26.7% | 35.3 | $12.00 | |
| 27 | Gemini 3.7 FlashGoogle | 26.7% | 69.9 | $3.75 | |
| 28 | Gemini 3.6 FlashGoogle | 23.3% | 48.3 | $3.75 | |
| 29 | Grok 4.5xAI | 22.5% | 75.5 | $6.00 | |
| 30 | Kimi K2.6Moonshot AI | 21.7% | 44.2 | $3.41 | |
| 31 | Mistral Large 4Mistral AI | 20.8% | 55.3 | $4.18 | |
| 32 | Grok 4.7xAI | 20.8% | 75.0 | $6.00 | |
| 33 | Qwen3.8 Max (0902)Qwen | 20.0% | 63.5 | $6.00 |
Only models in our catalog are listed, and each appears once with its best published run. 197 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.