GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
badtheorylabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
badtheorylabs
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Benchmark | BTL-4 | Base Ornith-1.0-35B | Harness |
|---|---|---|---|
| BFCL v4 (AST) | 73.5% | 69.2% | official ast_checker, all 1240 cases |
| LiveCodeBench v6 | 66.1% | — | official, 442 problems, 2024-08 → 2025-05 |
| SWE-bench Verified | 78.4% | — | official harness |
BFCL and LiveCodeBench were run in-house with the official scorers, full splits, no subsetting. The BFCL number is a paired comparison: identical harness, identical decoding, only the weights differ.
| pass@1 | |
|---|---|
| easy | 99.1% |
| medium | 86.7% |
| hard | 60.5% |
The set is 45% hard problems, which is what pulls the aggregate down.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "badtheorylabs/BTL-4"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16",device_map="auto")messages = [{"role": "user", "content": "Refactor this function to be pure."}]inputs = tok.apply_chat_template(messages, add_generation_prompt=True,return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=2048)print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
bash
vllm serve badtheorylabs/BTL-4 \--max-model-len 131072 \--enable-auto-tool-choice --tool-call-parser qwen3_xml \--reasoning-parser qwen3 \--trust-remote-code
llama.cpp, using the GGUF build:
bash
llama-server -m BTL-4-IQ2_XXS.gguf --port 8080 \--jinja \--reasoning-format deepseek \-c 32768 -fa on \--cache-type-k q8_0 --cache-type-v q8_0
Reasoning must be separated from content, on every stack. The chat template
strips reasoning from older turns, but only when the harness puts it in
reasoning_content. With vLLM that is --reasoning-parser qwen3; with
llama.cpp it is --reasoning-format deepseek. Without it, reasoning accumulates
into content each turn and the model repeats turns instead of terminating.
Ornith's published settings, used for every number above:
| temperature | 1.0 |
| top_p | 0.95 |
| context | 262144 native |
Give it room to think. LiveCodeBench improved 60.9% → 66.1% purely by raising the output budget from 16K to 32K. At 16K, 23.5% of problems were truncated mid-solution and scored zero. Hard problems reason longer; cutting them off costs real points.
reasoning_content. With vLLM, that means --reasoning-parser qwen3.
Without it, thinking lands in content, accumulates every turn, and long
agent runs degrade.Fine-tuned from Ornith-1.0-35B on an execution-gated reasoning corpus: candidate trajectories were kept only where the resulting code actually ran and passed its tests, so the reasoning that survived is reasoning that led somewhere.
bibtex
@misc{btl4-2026,title = {BTL-4: An Execution-Gated Agentic Reasoning Model},author = {Bad Theory Labs},year = {2026},url = {https://huggingface.co/badtheorylabs/BTL-4}}