# Toolathlon → BrowseComp

Calibration · https://benchgap.net/calibration/1516 · data retrieved 2026-10-29

BrowseComp is estimated from Toolathlon with a linear curve fitted on 13 models measured on both: y = 0.9612·x + 0.3158, R² = 0.85, cross-validated error 4.3 pp. It is used for 2 estimates.

| Estimated model | Toolathlon | BrowseComp | Source |
|---|---|---|---|
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 39.8% | 69.8% | estimated ± 4.3 pp, high confidence |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 26.9% | 57.4% | estimated ± 4.3 pp, medium confidence |

## Fitted on

| Model | Toolathlon | BrowseComp |
|---|---|---|
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 59.9% | 84.3% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 47.8% | 73.2% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 51.8% | 83.4% |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 38.0% | 62.0% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 54.6% | 82.7% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 55.6% | 84.4% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 53.4% | 83.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 58.0% | 92.2% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 53.1% | 87.5% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 50.0% | 83.2% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 27.8% | 60.6% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 36.3% | 69.0% |
| [Step 3.7 Flash](https://benchgap.net/model/step-3-7-flash.md) | 49.5% | 75.8% |