LLM Stats (PostTrainBench Lite): leaderboard
OpenAI's PostTrainBench Lite evaluation (adapted from PostTrainBench), as tracked by LLM Stats: agents get five hours on one H100 GPU to improve a pretrained base model (Qwen3-4B-Base, Qwen3-1.7B-Base or SmolLM3-3B-Base) on AIME 2025, BFCL, GSM8K or HumanEval (12 tasks, four attempts each). Scored in percent as mean share of the performance gap closed toward the developer's instruction-tuned reference (higher is better). LLM Stats combines GPT-6.2 Astra (including three replacement HumanEval attempts) and GPT-6.2 Sol from the GPT-6.2 system card (Table 5) with GPT-5.6 Terra, Sol and Luna from the GPT-5.6 launch post.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around April 2027. 5 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.2 Astra | 74.79 | #4 |
| 2 | GPT-5.6 Terra | 51.5 | #72 |
| 3 | GPT-5.6 Sol | 50.3 | #36 |
| 4 | GPT-6.2 Sol | 44.89 | #12 |
| 5 | GPT-5.6 Luna | 29.6 | #133 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #5 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-posttrainbench-lite · How It Works · Data refreshed daily, snapshot 2026-11-20.