List your company

Code on LiveCode

83.6AccuracyLowest Centroid
37.94449.79761.6573.503Apr 28, 2026

Evaluation results

MethodLinks
Lowest CentroidModel=GPT-OSS-120B, Number of Samples=322026.0483.6
Greedy DecodingModel=GPT-OSS-120B, Number of Samples=322026.0482
Bottom WindowModel=GPT-OSS-120B, Number of Samples=322026.0481.3
Pass@1Model=GPT-OSS-120B, Number of Samples=322026.0481.2
Self-CertaintyModel=GPT-OSS-120B, Number of Samples=322026.0480.3
Tail ConfidenceModel=GPT-OSS-120B, Number of Samples=322026.0480.1
Self-CertaintyModel=Qwen3-14B, Number of Samples=322026.0479.5
Tail ConfidenceModel=Qwen3-14B, Number of Samples=322026.0478.6
Lowest CentroidModel=Qwen3-14B, Number of Samples=322026.0478.1
Self-CertaintyModel=QWQ-32B, Number of Samples=322026.0478.1
Lowest CentroidModel=QWQ-32B, Number of Samples=322026.0478
Bottom WindowModel=QWQ-32B, Number of Samples=322026.0477.9
Bottom WindowModel=Qwen3-14B, Number of Samples=322026.0477.7
Tail ConfidenceModel=QWQ-32B, Number of Samples=322026.0477.4
Lowest CentroidModel=Olmo-3.1-Think, Number of Samples=322026.0477.2
Pass@1Model=Qwen3-14B, Number of Samples=322026.0477.2
Pass@1Model=QWQ-32B, Number of Samples=322026.0476.7
Self-CertaintyModel=Olmo-3.1-Think, Number of Samples=322026.0476.6
Tail ConfidenceModel=Olmo-3.1-Think, Number of Samples=322026.0476.3
Bottom WindowModel=Olmo-3.1-Think, Number of Samples=322026.0475.9
Pass@1Model=Olmo-3.1-Think, Number of Samples=322026.0474.2
Greedy DecodingModel=QWQ-32B, Number of Samples=322026.0473.2
Greedy DecodingModel=Qwen3-14B, Number of Samples=322026.0472.6
Greedy DecodingModel=Olmo-3.1-Think, Number of Samples=322026.0471.6
Tail ConfidenceModel=Ministral-3-14B-Instruct, Number of Samples=322026.0446.8
Bottom WindowModel=Ministral-3-14B-Instruct, Number of Samples=322026.0444.5
Lowest CentroidModel=Ministral-3-14B-Instruct, Number of Samples=322026.0444.4
Pass@1Model=Ministral-3-14B-Instruct, Number of Samples=322026.0440.3
Self-CertaintyModel=Ministral-3-14B-Instruct, Number of Samples=322026.0440
Greedy DecodingModel=Ministral-3-14B-Instruct, Number of Samples=322026.0439.7