TPS-CalcBench - Level 4: leaderboard
Metric: Composite KPI (0-100): mean rubric-weighted process score (formula selection, parameters, units, calculation accuracy, plausibility, assumptions, interpretation, presentation, each judged 0 to 2 by a calibrated Gemini-3-Pro-Preview judge against the reference solution) over the successfully judged items of the 50 level-4 (advanced iterative or coupled) items on the 420-item high-confidence core set of TPS-CalcBench (analytical calculation problems in hypersonic thermal protection system engineering), zero-shot text-only prompting; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 98 |
| 2 | GPT-5.1 | 95 |
| 3 | GLM-5 | 75 |
| 4 | DeepSeek V3.1 | 67 |
| 5 | GLM-4.7 | 64 |
| 6 | Claude Opus 4.5 | 58.4 |
Interactive version: theaggregate.ai/benchmark?slug=tps-calcbench-level-4 · How It Works · Data refreshed daily, snapshot 2026-10-07.