List your company

Code on CRUX

55.08Accuracy @5CoReward
5.617618.458831.344.1412Apr 28, 2026

Evaluation results

MethodLinks
CoRewardBackbone=Qwen2.5-7B2026.0455.08—
JURY-RLBackbone=Qwen2.5-7B2026.0454.37—
GT-RewardBackbone=Qwen2.5-7B2026.0453.67—
LLM-KDBackbone=Qwen2.5-7B2026.0453.57—
Self-CertaintyBackbone=Qwen2.5-7B2026.0453.18—
Majority-VotingBackbone=Qwen2.5-7B2026.0452.2—
LLM-as-a-JudgeBackbone=Qwen2.5-7B2026.0451.9—
EntropyBackbone=Qwen2.5-7B2026.0451.08—
LLM-as-a-JudgeBackbone=Qwen3-1.7B-Base2026.0434.98—
CoRewardBackbone=Qwen3-1.7B-Base2026.0434.1—
JURY-RLBackbone=Qwen3-1.7B-Base2026.0433.98—
LLM-KDBackbone=Qwen3-1.7B-Base2026.0433.8—
GT-RewardBackbone=Qwen3-1.7B-Base2026.0433.73—
GT-RewardBackbone=Llama-3.2-3B-Instruct2026.0432.48—
Majority-VotingBackbone=Qwen3-1.7B-Base2026.0432—
JURY-RLBackbone=Llama-3.2-3B-Instruct2026.0431.6—
LLM-as-a-JudgeBackbone=Llama-3.2-3B-Instruct2026.0431.45—
LLM-KDBackbone=Llama-3.2-3B-Instruct2026.0431.2—
CoRewardBackbone=Llama-3.2-3B-Instruct2026.0430.87—
Majority-VotingBackbone=Llama-3.2-3B-Instruct2026.0430.83—
EntropyBackbone=Qwen3-1.7B-Base2026.0430.38—
Before RLBackbone=Qwen2.5-7B2026.0427.38—
EntropyBackbone=Llama-3.2-3B-Instruct2026.0426.3—
Before RLBackbone=Llama-3.2-3B-Instruct2026.0424.7—
Self-CertaintyBackbone=Llama-3.2-3B-Instruct2026.0424.55—
Self-CertaintyBackbone=Qwen3-1.7B-Base2026.0418.73—
Before RLBackbone=Qwen3-1.7B-Base2026.047.52—
NPG-Muse-7BBackbone=Qwen2.5-7B-Instruct-1M2025.08—59
NPG-Muse-8BBackbone=Qwen3-8B-Base2025.08—65.3
Qwen2.5-14B-Instruct-1MSize=14B, Type=Instruct, Context Length=1M2025.08—66.4
Qwen2.5-7B-Instruct-1MSize=7B, Type=Instruct, Context Length=1M2025.08—55.6
Qwen3-14B-BaseSize=14B, Type=Base2025.08—63.9
Qwen3-8B-BaseSize=8B, Type=Base2025.08—54.1