List your company
ResearchFormerly WizWand

Reasoning on Reasoning-Gym (test)

70.1AccuracyR1-CI
6.34822.89939.4556.001May 27, 2025
Updated 8mo ago

Evaluation results

MethodLinks
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI2025.0570.1
GPT-4oModel=GPT-4o, Evaluation Strategy=Code Interpreter2025.0568.4
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI2025.0564.3
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo IP2025.0563.5
Qwen3-14BModel=Qwen3-14B, Evaluation Strategy=CodeSteer2025.0562.1
Qwen3-14BModel=Qwen3-14B, Evaluation Strategy=All Text2025.0560.5
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo IP2025.0560.1
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo CL2025.0560
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo CL2025.0557.9
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo GRPO2025.0556.1
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI2025.0554.9
GPT-4oModel=GPT-4o, Evaluation Strategy=All Text2025.0554.6
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo GRPO2025.0553.6
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo IP2025.0550.3
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo CL2025.0548.1
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo GRPO2025.0544
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=CodeSteer2025.0540.5
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.0539.7
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=All Text2025.0539.6
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=All Code2025.0535.7
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=All Code2025.0534
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=CodeSteer2025.0529.3
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.0527
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=All Text2025.0526.3
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=CodeSteer2025.0511.5
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=All Text2025.0510.7
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=All Code2025.058.9
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.058.8