Noometry

Multimodal benchmark

Furniture Assembly leaderboard

As of October 2026, Claude Opus 5.5 has the highest published Furniture Assembly score on Noometry at 83.3%, out of 31 models with results.

Last verified

About Furniture Assembly

A description with primary sources is being prepared for this benchmark.

Category
Multimodal
Introduced
2026
Unit
Percent (random guessing ≈ 30%)
Official site
epoch.ai

Top 15 models

  1. Claude Opus 5.5 83.3%
  2. GPT-6.1 Sol 80%
  3. GPT-6 Astra 80%
  4. Claude Sonnet 5.5 75%
  5. Claude Fable 5.1 70%
  6. Claude Opus 5 60.8%
  7. GPT-6 Sol 58.3%
  8. GPT-5.6 Sol 56.7%
  9. GPT-5.6 Terra 54.2%
  10. Claude Haiku 5.5 47.5%
  11. GPT-5.5 44.2%
  12. GPT-6 Luna 44.2%
  13. Claude Opus 4.8 42.5%
  14. GPT-5.6 Luna 42.5%
  15. Grok 4.6 40%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Claude Opus 5.5 Anthropic83.3%maxEpoch AI2026-09-22
2GPT-6.1 Sol OpenAI80%maxEpoch AI2026-09-29
3GPT-6 Astra OpenAI80%maxEpoch AI2026-09-10
4Claude Sonnet 5.5 Anthropic75%maxEpoch AI2026-09-29
5Claude Fable 5.1 Anthropic70%maxEpoch AI2026-09-10
6Claude Opus 5 Anthropic60.8%maxEpoch AI2026-09-10
7GPT-6 Sol OpenAI58.3%maxEpoch AI2026-09-23
8GPT-5.6 Sol OpenAI56.7%maxEpoch AI2026-09-10
9GPT-5.6 Terra OpenAI54.2%maxEpoch AI2026-09-10
10Claude Haiku 5.5 Anthropic47.5%maxEpoch AI2026-10-07
11GPT-5.5 OpenAI44.2%xhighEpoch AI2026-09-10
12GPT-6 Luna OpenAI44.2%maxEpoch AI2026-09-28
13Claude Opus 4.8 Anthropic42.5%maxEpoch AI2026-09-10
14GPT-5.6 Luna OpenAI42.5%maxEpoch AI2026-09-10
15Grok 4.6 xAI40%xhighEpoch AI2026-09-24
16GPT-5.2 OpenAI38.3%xhighEpoch AI2026-09-10
17GPT-5.4 OpenAI37.5%xhighEpoch AI2026-09-10
18Claude Fable 5 Anthropic35.8%maxEpoch AI2026-09-10
19DeepSeek V4.1 Flash DeepSeek34.2%maxEpoch AI2026-10-08
20Kimi K3 Moonshot AI34.2%maxEpoch AI2026-09-11
21Claude Opus 4.7 Anthropic33.3%maxEpoch AI2026-09-10
22Gemini 3.8 Flash Google31.7%highEpoch AI2026-09-10
23Claude Opus 4.5 Anthropic28.3%64KEpoch AI2026-09-10
24Claude Opus 4.6 Anthropic28.3%maxEpoch AI2026-09-10
25Gemini 3.1 Pro Preview Google26.7%highEpoch AI2026-09-10
26Gemini 3.7 Flash Google26.7%highEpoch AI2026-09-10
27Gemini 3.6 Flash Google23.3%highEpoch AI2026-09-10
28Grok 4.5 xAI22.5%highEpoch AI2026-09-24
29Kimi K2.6 Moonshot AI21.7%Epoch AI2026-09-11
30Grok 4.7 xAI20.8%xhighEpoch AI2026-09-24
31Qwen3.8 Max Alibaba (Qwen)20%xhighEpoch AI2026-09-10

Compare the leaders

Other multimodal benchmarks

Frequently asked questions

Which model has the highest Furniture Assembly score?

As of October 2026, Claude Opus 5.5 has the highest published Furniture Assembly score on Noometry at 83.3%, out of 31 models with results.

What is the best open-weight model on Furniture Assembly?

DeepSeek V4.1 Flash has the highest Furniture Assembly accuracy among open-weight models at 34.2%, ranking 19 of 31 overall.