List your company
ResearchFormerly WizWand

Mathematical Problem Solving on AIME 2024 (Pass@1, Avg)

76Pass@1Qwen3-8B
-3.0417.483858.52Jul 17, 2025Aug 24, 2025Oct 1, 2025Nov 8, 2025Dec 16, 2025Jan 23, 2026Mar 2, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Qwen3-8Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0776—
DeepSeek-R1-Distill-32Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0772.6—
QUESTA-Nemotron-1.5Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0772.5—
Nemotron-1.5Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0761.77—
Qwen3-1.7Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0748.3—
Qwen-2-7B w/ T3RLModel Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=T3RL2026.034068.1
Qwen-2-7B w/ TTRLModel Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=TTRL2026.0336.465.5
DeepSeek-R1-Distill-1.5Bk (responses per question)=32, sampling temperature=0.7, top-p=0.952025.0728.7—
Qwen-2.5-Math-1.5B w/ T3RLModel Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=T3RL2026.0320.848.8
Llama-3-8B-Instruct w/ T3RLModel Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=T3RL2026.0317.138.2
Qwen-2.5-Math-1.5B w/ TTRLModel Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=TTRL2026.0315.845.9
Llama-3-8B-Instruct w/ TTRLModel Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=TTRL2026.0313.335.4
Llama-3.2-1B-Instruct w/ T3RLModel Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=T3RL2026.038.323.5
Qwen-2.5-Math-1.5B (Baseline)Model Category=Math Model, Backbone=Qwen-2.5-Math-1.5B, Training Method=Baseline2026.037.723
Llama-3.2-1B-Instruct w/ TTRLModel Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=TTRL2026.037.521.5
Llama-3-8B-Instruct (Baseline)Model Category=Instruct Model, Backbone=Llama-3-8B-Instruct, Training Method=Baseline2026.03623.1
Qwen-2.5-1.5B w/ T3RLModel Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=T3RL2026.034.133.3
Qwen-2.5-1.5B w/ TTRLModel Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=TTRL2026.033.531.8
Llama-3.2-1B-Instruct (Baseline)Model Category=Instruct Model, Backbone=Llama-3.2-1B-Instruct, Training Method=Baseline2026.030.83.1
Qwen-2.5-1.5B (Baseline)Model Category=Vanilla Model, Backbone=Qwen-2.5-1.5B, Training Method=Baseline2026.030.22.8
Qwen-2-7B (Baseline)Model Category=Vanilla Model, Backbone=Qwen-2-7B, Training Method=Baseline2026.03021