List your company
ResearchFormerly WizWand

Reasoning on Reasoning-Gym (train)

63.3AccuracyGPT-4o
2.66818.40934.1549.891May 27, 2025
Updated 8mo ago

Evaluation results

MethodLinks
GPT-4oModel=GPT-4o, Evaluation Strategy=Code Interpreter2025.0563.3
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI2025.0558.9
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo IP2025.0554.4
Qwen3-14BModel=Qwen3-14B, Evaluation Strategy=CodeSteer2025.0553.8
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI2025.0553.6
Qwen3-14BModel=Qwen3-14B, Evaluation Strategy=All Text2025.0552.9
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo CL2025.0552.8
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo IP2025.0550.8
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo CL2025.0549.1
R1-CIModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=R1-CI wo GRPO2025.0548.3
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI2025.0546.6
R1-CIModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=R1-CI wo GRPO2025.0545.6
GPT-4oModel=GPT-4o, Evaluation Strategy=All Text2025.0545.5
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo IP2025.0542.5
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo CL2025.0540.9
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=All Code2025.0540.4
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=CodeSteer2025.0537.8
R1-CIModel=Qwen2.5-3B-Instruct, Evaluation Strategy=R1-CI wo GRPO2025.0536.9
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=All Text2025.0535.8
Qwen2.5-14B-Instruct-1MModel=Qwen2.5-14B-Instruct-1M, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.0530
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=CodeSteer2025.0526.4
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=All Text2025.0525.7
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=All Code2025.0525.7
Qwen2.5-7B-Instruct-1MModel=Qwen2.5-7B-Instruct-1M, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.0520
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=All Text2025.0511.2
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=CodeSteer2025.058.9
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=Code Agent (CI wo Fine-tune)2025.055.4
Qwen2.5-3B-InstructModel=Qwen2.5-3B-Instruct, Evaluation Strategy=All Code2025.055