# Toolathlon-Verified → OSWorld 2.0

Calibration · https://benchgap.net/calibration/1538 · data retrieved 2026-10-29

OSWorld 2.0 is estimated from Toolathlon-Verified with a offset logistic curve fitted on 5 models measured on both: y = 0.1939 + (0.7079 − 0.1939) / (1 + exp(−199.98·(x − 0.7780))), R² = 0.99, cross-validated error 5.5 pp. It is used for 10 estimates.

| Estimated model | Toolathlon-Verified | OSWorld 2.0 | Source |
|---|---|---|---|
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 78.4% | 59.0% | estimated ± 5.5 pp, low confidence |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 77.8% | 45.2% | estimated ± 5.5 pp, low confidence |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 74.1% | 19.4% | estimated ± 5.5 pp, low confidence |
| [Hy4 preview](https://benchgap.net/model/hy4-preview.md) | 74.1% | 19.4% | estimated ± 5.5 pp, low confidence |
| [Step 5 Preview](https://benchgap.net/model/step-5-preview.md) | 74.1% | 19.4% | estimated ± 5.5 pp, low confidence |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 73.2% | 19.4% | estimated ± 5.5 pp, low confidence |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 73.0% | 19.4% | estimated ± 5.5 pp, low confidence |
| [Muse Spark Open](https://benchgap.net/model/muse-spark-open.md) | 72.8% | 19.4% | estimated ± 5.5 pp, low confidence |
| [Ornith-1.5-397B](https://benchgap.net/model/ornith-1-5-397b.md) | 71.2% | 19.4% | estimated ± 5.5 pp, low confidence |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 70.3% | 19.4% | estimated ± 5.5 pp, low confidence |

## Fitted on

| Model | Toolathlon-Verified | OSWorld 2.0 |
|---|---|---|
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 77.8% | 41.7% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 80.6% | 70.6% |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 77.8% | 48.7% |
| [Qwen3.8-Flash-Next](https://benchgap.net/model/qwen3-8-flash-next.md) | 73.5% | 19.4% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 72.5% | 19.4% |