GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
benjkoch
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
benjkoch
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| stage | persona (Qwen rubric, 0–1) | MATH-500 % | GSM8K % | AIME 2024 % |
|---|---|---|---|---|
| SFT | 0.826 | 67.6 | 85.2 | 6.7 |
| RLAIF | 0.828 | 66.2 | 86.0 | 3.3 |
| pure RLVR | 0.825 | 67.0 | 85.6 | 6.7 |
| mixed RLVR + persona | 0.825 | 68.0 | 86.4 | 10.0 |
None of these differences is statistically detectable. Against the RLAIF starting model, MATH-500 +1.8 pp
(28 gained / 19 lost, McNemar p = 0.24), GSM8K +0.4 pp, and persona -0.003 (95% bootstrap CI -0.008 to +0.002). An
independent Mistral-Small-24B-Instruct-2501 judge, on 100 held-out rows in both answer orders, found 1 win / 97
ties / 2 losses against RLAIF and 5 / 89 / 6 against SFT. The persona survived continued math training, and math
did not measurably improve at this training scale (one epoch over 400 fresh questions, lr 5e-6).
Paired tests, uncertainty, the beta sweep and the reward-gaming audit are in the report. A correct final answer is outcome accuracy, not proof of correct reasoning.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", dtype="bfloat16")model = PeftModel.from_pretrained(model, "benjkoch/Qwen2.5-3B-Instruct-Sheldon-RLVR")Use prompts/sheldon_system.txt
as the system message; the model was trained and evaluated with it.