GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DubbyDu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
DubbyDu
Model Tree
Input Modalities
Output Modalities
Supported Functionality
We primarily evaluate our trained models on MLE-Bench Lite, a 22-task subset of MLE-Bench consisting of historical Kaggle competitions for end-to-end machine learning engineering. We report the percentage of tasks awarded each medal tier (Gold, Silver, and Bronze), the percentage receiving any medal (Any Medal), and the percentage exceeding the median human score (Med+), with Any Medal as the primary metric. All five metrics are computed over the 22 tasks and reported as percentages.
The first five metric columns use the M1 Harness; the last two columns report the general-purpose harness and its medal rate. All values are percentages.
M1 achieves the highest medal rate among same-scale models and reaches the performance level of larger frontier models. Under the unified M1 Harness, M1 raises the medal rate of its Qwen3.6-35B-A3B base model from 37.9% to 72.7%, achieving the highest rate among the same-scale models evaluated and performance comparable to GLM-5.3 and Kimi-K3. These results show that long-horizon agentic post-training substantially improves the base model's MLE capability, bringing a 35B model to a performance level comparable to larger frontier models.
M1 retains its advantage over the base model under a general-purpose coding harness. With Claude Code, M1 achieves a 69.7% medal rate, compared with 42.4% for its base model, and exceeds the strongest evaluated same-scale baseline by 22.7 percentage points. The consistent advantage over the base model across both harnesses suggests that the improvement from post-training is not specific to the M1-Harness and remains effective in a general-purpose agentic coding environment.
We also evaluate on NatureBench, following the ten-task Lite subset used in Frontis-MA1. M denotes Match-SOTA (g ≥ 0), while S denotes Surpass-SOTA (g > 0.1), which serves as a key metric for directly assessing agents' ability to surpass published scientific results.
On NatureBench Lite, M1 improves scientific task performance over the base model. With Claude Code, M1 raises the Surpass-SOTA rate from 0.0% to 50.0%, exceeding Nex-N2.5-mini at 20.0% and matching GLM-5.3 at 50.0%. Its Match-SOTA rate also improves from 40.0% to 70.0%. These results show that post-training improves scientific task optimization, enabling M1 to match or exceed published reference results on more tasks.
The commands below load DubbyDu/M1 and serve an API endpoint at http://localhost:8000/v1.
Install SGLang with uv:
shell
uv venv --python 3.12 --seed --managed-pythonsource .venv/bin/activateuv pip install sglangText Generation
shell
python -m sglang.launch_server \ --model-path DubbyDu/M1 \ --host 127.0.0.1 \ --port 8000 \ --tp-size 2 \ --context-length 262144 \ --reasoning-parser qwen3 \ --language-model-onlyTool Use
shell
python -m sglang.launch_server \ --model-path DubbyDu/M1 \ --host 127.0.0.1 \ --port 8000 \ --tp-size 2 \ --context-length 262144 \ --reasoning-parser qwen3 \ --tool-call-parser qwen3_coder \ --language-model-onlyInstall vLLM with uv:
shell
uv venv --python 3.12 --seed --managed-pythonsource .venv/bin/activateuv pip install vllm --torch-backend=autoText Generation
shell
vllm serve DubbyDu/M1 \ --host 127.0.0.1 \ --port 8000 \ --tensor-parallel-size 2 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --language-model-onlyTool Calling
shell
vllm serve DubbyDu/M1 \ --host 127.0.0.1 \ --port 8000 \ --tensor-parallel-size 2 \ --max-model-len 262144 \ --reasoning-parser qwen3 \ --enable-auto-tool-choice \ --tool-call-parser qwen3_coder \ --language-model-onlyThe two M1 inference profiles use the same sampling parameters and differ in whether thinking is enabled. The machine-readable profiles are provided in inference_profiles.json.
| Parameter | Thinking | Non-thinking |
|---|---|---|
temperature | 1.0 | 1.0 |
top_p | 0.95 | 0.95 |
top_k | 20 | 20 |
min_p | 0.0 | 0.0 |
Use thinking mode for coding and experimental reasoning. Non-thinking mode provides direct responses for planner or structured-output calls.
Set chat_template_kwargs.enable_thinking to true for thinking mode or false for non-thinking mode. The deployment commands above use the qwen3 reasoning parser and, for tool use, the qwen3_coder tool-call parser.
presence_penalty| 1.5 |
| 1.5 |
repetition_penalty | 1.0 | 1.0 |
enable_thinking | true | false |