# SuperGPQA → HLE

Calibration · https://benchgap.net/calibration/1448 · data retrieved 2026-10-29

HLE is estimated from SuperGPQA with a offset logistic curve fitted on 14 models measured on both: y = 0.0585 + (0.5113 − 0.0585) / (1 + exp(−19.17·(x − 0.6886))), R² = 0.94, cross-validated error 4.8 pp. It is used for 8 estimates.

| Estimated model | SuperGPQA | HLE | Source |
|---|---|---|---|
| [Qwen 3.6 Max (preview)](https://benchgap.net/model/qwen3-6-max-preview.md) | 73.9% | 38.6% | estimated ± 4.8 pp, high confidence |
| [Seed 2.1 Pro](https://benchgap.net/model/seed-2-1-pro.md) | 70.8% | 32.6% | estimated ± 4.8 pp, high confidence |
| [Seed 2.1 Turbo](https://benchgap.net/model/seed-2-1-turbo.md) | 67.4% | 25.3% | estimated ± 4.8 pp, high confidence |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 67.1% | 24.7% | estimated ± 4.8 pp, high confidence |
| [Qwen3.5-27B](https://benchgap.net/model/qwen3-5-27b.md) | 65.6% | 21.6% | estimated ± 4.8 pp, high confidence |
| [Qwen3.5-35B-A3B](https://benchgap.net/model/qwen3-5-35b-a3b.md) | 63.4% | 17.6% | estimated ± 4.8 pp, high confidence |
| [Qwen3 235B 2507](https://benchgap.net/model/qwen3-235b-2507.md) | 62.6% | 16.3% | estimated ± 4.8 pp, high confidence |
| [MiniCPM5-1B](https://benchgap.net/model/minicpm5-1b.md) | 23.1% | 5.9% | estimated ± 4.8 pp, medium confidence |

## Fitted on

| Model | SuperGPQA | HLE |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 70.6% | 30.8% |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 95.0% | 53.0% |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 95.0% | 49.0% |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 66.8% | 30.5% |
| [Kimi K2](https://benchgap.net/model/kimi-k2.md) | 57.2% | 4.7% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 69.2% | 30.1% |
| [MiniCPM5-2B](https://benchgap.net/model/minicpm5-2b.md) | 40.8% | 8.9% |
| [Qwen3 235B 2507 (Reasoning)](https://benchgap.net/model/qwen3-235b-2507-reasoning.md) | 64.9% | 18.2% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 70.4% | 28.7% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 66.0% | 24.0% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 64.7% | 21.4% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 71.6% | 28.8% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 73.6% | 41.4% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 71.4% | 34.7% |