TPS-CalcBench - Level 2: 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 120 level-2 (multi-step) 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: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.1 | 81.5 |
| 2 | GPT-5.2 | 81.1 |
| 3 | Claude Opus 4.5 | 79.4 |
| 4 | GPT-5.1 | 77.7 |
| 5 | GLM-4.7 | 71.1 |
| 6 | GLM-5 | 70.6 |
Interactive version: theaggregate.ai/benchmark?slug=tps-calcbench-level-2 · How It Works · Data refreshed daily, snapshot 2026-10-07.