Calibration
WideResearch → JobBench
JobBench is estimated from WideResearch with a linear curve fitted on 5 models measured on both: y = 4.4991·x + -3.1576, R² = 0.98, cross-validated error 5.1 pp. It is used for 5 estimates.
| Estimated model | WideResearch | JobBench | Source |
|---|---|---|---|
| GLM-5 | 69.8% | 0.0% | estimated ± 5.1 pp, low confidence |
| Ling 3.0 Flash | 73.6% | 15.4% | estimated ± 5.1 pp, low confidence |
| Qwen3.5 397B | 74.0% | 17.2% | estimated ± 5.1 pp, low confidence |
| Qwen3.6-35B-A3B | 60.1% | 0.0% | estimated ± 5.1 pp, low confidence |
| Qwen3.6 Plus | 74.3% | 18.5% | estimated ± 5.1 pp, low confidence |