List your company

Planning on FORGE-BENCH

99Success Rate (SR)FORGE-7B-NP-MATH
-3.4423.15549.7576.345May 9, 2026

Evaluation results

MethodLinks
FORGE-7B-NP-MATHModel Category=Open-Source LLMs2026.059932.3
FORGE-7B-NPModel Category=Open-Source LLMs2026.0598.228.9
gpt-o3Model Category=Proprietary LLMs2026.057465.1
DS-V3.1-ThinkingModel Category=Proprietary LLMs2026.0561.954.3
Qwen3-235B-ThinkingModel Category=Proprietary LLMs2026.055244.8
gpt-4o-2024-08-06Model Category=Proprietary LLMs2026.055229.6
Qwen3-30B-A3BModel Category=Open-Source LLMs2026.0544.536.9
Qwen2.5-32BModel Category=Open-Source LLMs2026.0523.56.7
QWEN2.5-7B-SFTModel Category=Open-Source LLMs2026.052216.8
Qwen3-32BModel Category=Open-Source LLMs2026.0521.611.2
Qwen2.5-14BModel Category=Open-Source LLMs2026.0517.54.9
InternLM3-8bModel Category=Open-Source LLMs2026.05164.1
Qwen3-235B-InstructModel Category=Proprietary LLMs2026.0515.58.3
Qwen2.5-3BModel Category=Open-Source LLMs2026.0515.53.7
DS-R1-Qwen-32BModel Category=Open-Source LLMs2026.0515.47.9
LLama3.1-8BModel Category=Open-Source LLMs2026.05151.8
Qwen2.5-72BModel Category=Open-Source LLMs2026.056.52.1
DS-R1-Qwen-14BModel Category=Open-Source LLMs2026.054.51.4
Qwen2.5-7BModel Category=Open-Source LLMs2026.053.51
Qwen3-8BModel Category=Open-Source LLMs2026.0531.2
DS-R1-Qwen-7BModel Category=Open-Source LLMs2026.050.50.1