Update README.md

README.md

@@ -85,41 +85,7 @@ loop on the teacher too** (intrinsic); the other ~3.6 points are the price of pr
 
 > A **knowledge-recovery LoRA** (separate, optional adapter) is being trained to add capacity back and
 > close this gap — see the model index. The pruned model remains a strong ~34%-smaller option; just
-> know it trades ~3.6 points of termination robustness for the size.
-
-## Coding benchmark results
-
-These scores are for `0xSero/GLM-5.2-504B` (REAP keep-168 + Router-KD, NVFP4) served through an OpenAI-compatible endpoint.
-
-| Benchmark | Score | Notes |
-|---|---:|---|
-| Terminal-Bench 2.1 full-89 | **70.5%** | Locked 89-task board-faithful config, 5 attempts, `terminus-2`, `reasoning_effort=max`, temperature 1.0. |
-| Aider Polyglot | **90.1%** | Aggregate language score across Python, JavaScript, Java, C++, Go, and Rust. |
-
-### Aider Polyglot language breakdown
-
-`FULL` is the unpruned GLM-5.2 baseline. `REAP` is this 504B REAP + Router-KD checkpoint. Scores are percentages.
-
-| Language | FULL | REAP | Change |
-|---|---:|---:|---:|
-| Python | 97.1 | 94.1 | -3.0 |
-| JavaScript | 93.9 | 93.9 | 0.0 |
-| Java | 85.1 | 85.1 | 0.0 |
-| C++ | 92.3 | 96.2 | +3.9 |
-| Go | 89.7 | 87.2 | -2.5 |
-| Rust | 86.7 | 83.3 | -3.4 |
-
-## Serving (vLLM)
-
-```bash
-vllm serve 0xSero/GLM-5.2-504B \
-  --tensor-parallel-size 8 \
-  --quantization modelopt_fp4 \
-  --kv-cache-dtype fp8 \
-  --trust-remote-code \
-  --max-model-len 262144
-```
-
+> know it trades ~3.6 points of termination robustness for the 
 ### Recommended serving — recover most of the loop gap for free
 
 Two no-retrain knobs, measured at n=2000: