# GPQA → ARC-AGI-3

Calibration · https://benchgap.net/calibration/gpqa/current/to/arcagi3/current · data retrieved 2026-11-18

ARC-AGI-3 is estimated from GPQA with a offset logistic curve fitted on 12 models measured on both: y = 0.0000 + (0.7656 − 0.0000) / (1 + exp(−200.00·(x − 0.9548))), R² = 0.99, cross-validated error 9.3 pp. It is used for 4 estimates.

| Estimated model | GPQA | ARC-AGI-3 | Source |
|---|---|---|---|
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 88.4% | 0.0% | estimated ± 9.3 pp, low confidence |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 87.8% | 0.0% | estimated ± 9.3 pp, low confidence |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 86.6% | 0.0% | estimated ± 9.3 pp, low confidence |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 86.0% | 0.0% | estimated ± 9.3 pp, low confidence |

## Fitted on

| Model | GPQA | ARC-AGI-3 |
|---|---|---|
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 91.3% | 0.5% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 94.2% | 0.2% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 93.6% | 1.5% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 92.8% | 0.2% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 93.6% | 0.4% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 92.3% | 0.2% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 94.6% | 7.8% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 92.9% | 0.8% |
| [GPT-6.2 Astra](https://benchgap.net/model/gpt-6-2-astra.md) | 97.0% | 70.3% |
| [GPT-6.2 Sol](https://benchgap.net/model/gpt-6-2-sol.md) | 96.0% | 54.9% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 96.0% | 62.7% |
| [Inkling 2 Small](https://benchgap.net/model/inkling-2-small.md) | 93.0% | 0.3% |
