List your company

Mathematical Problem Solving on AMC (Pass@1, Avg)

74.2Pass@1Qwen-2-7B w/ T3RL
-2.34417.52837.457.272Mar 2, 2026

Evaluation results

MethodLinks
Qwen-2-7B w/ T3RLModel Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=T3RL2026.0374.268.1
Qwen-2-7B w/ TTRLModel Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=TTRL2026.0371.765.5
Qwen-2.5-Math-1.5B w/ T3RLModel Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=T3RL2026.0350.948.8
Qwen-2.5-Math-1.5B w/ TTRLModel Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=TTRL2026.0348.945.9
Llama-3-8B-Instruct w/ T3RLModel Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=T3RL2026.0334.238.2
Llama-3-8B-Instruct w/ TTRLModel Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=TTRL2026.0331.335.4
Qwen-2.5-1.5B w/ T3RLModel Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=T3RL2026.0330.733.3
Qwen-2.5-Math-1.5B (Baseline)Model Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=Baseline2026.0328.623
Qwen-2.5-1.5B w/ TTRLModel Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=TTRL2026.0328.631.8
Llama-3.2-1B-Instruct w/ T3RLModel Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=T3RL2026.0319.923.5
Llama-3-8B-Instruct (Baseline)Model Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=Baseline2026.0319.423.1
Llama-3.2-1B-Instruct w/ TTRLModel Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=TTRL2026.0316.921.5
Qwen-2-7B (Baseline)Model Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=Baseline2026.0312.521
Llama-3.2-1B-Instruct (Baseline)Model Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=Baseline2026.034.23.1
Qwen-2.5-1.5B (Baseline)Model Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=Baseline2026.030.62.8