# Furniture Assembly → MaxxBench

Calibration · https://benchgap.net/calibration/furnitureassembly/current/to/maxxbench/current · data retrieved 2026-11-18

MaxxBench is estimated from Furniture Assembly with a linear curve fitted on 10 models measured on both: y = 0.3991·x + 0.4009, R² = 0.65, cross-validated error 6.6 pp. It is used for 4 estimates.

| Estimated model | Furniture Assembly | MaxxBench | Source |
|---|---|---|---|
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 26.7% | 50.7% | estimated ± 6.6 pp, low confidence |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 23.3% | 49.4% | estimated ± 6.6 pp, low confidence |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 22.5% | 49.1% | estimated ± 6.6 pp, low confidence |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 21.7% | 48.8% | estimated ± 6.6 pp, low confidence |

## Fitted on

| Model | Furniture Assembly | MaxxBench |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 35.8% | 63.5% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 60.8% | 63.5% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 83.3% | 76.4% |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 75.0% | 66.9% |
| [DeepSeek V4.1 Flash 1017](https://benchgap.net/model/deepseek-v4-1-flash.md) | 34.2% | 55.6% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 31.7% | 53.4% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 42.5% | 46.1% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 56.7% | 69.1% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 80.0% | 71.9% |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 44.2% | 51.7% |
