List your company

Closed-ended reasoning on GPQA Diamond (test)

65.9AccuracyMajority Voting (MV)
42.91648.88354.8560.817Dec 2, 2025

Evaluation results

MethodLinks
Majority Voting (MV)K=8, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1265.9
Majority Voting (MV)K=4, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1265.2
THINKMERGE (DirectMerge (A))K=8, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1264.1
Majority Voting (MV)K=8, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1264.1
THINKMERGE (Ours (C))K=8, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1264.1
THINKMERGE (DirectMerge (A))K=4, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1264
Majority Voting (MV)K=4, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1264
Majority Voting (MV)K=8, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1263.9
THINKMERGE (Ours (D))K=4, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1263.8
THINKMERGE (Ours (D))K=2, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1263.7
THINKMERGE (Ours (D))K=8, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1263.7
Majority Voting (MV)K=2, Backbone=Qwen3-14B, Strategy=Shortest-K Merge2025.1263.4
Majority Voting (MV)K=4, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1263
THINKMERGE (Trimming (B))K=8, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1263
THINKMERGE (Trimming (B))K=4, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1262.7
THINKMERGE (Ours (C))K=4, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1262.4
THINKMERGE (Ours (C))K=2, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1262.1
THINKMERGE (DirectMerge (A))K=2, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1261.6
THINKMERGE (Trimming (B))K=2, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1261.4
Majority Voting (MV)K=2, Backbone=Qwen3-14B, Strategy=All-Reduce2025.1260.8
Majority Voting (MV)K=2, Backbone=Qwen3-14B, Strategy=Early-Ready2025.1260.8
Majority Voting (MV)K=8, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1255.5
THINKMERGE (Ours (D))K=8, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1253.8
Majority Voting (MV)K=4, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1253.7
Majority Voting (MV)K=8, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1253.3
Majority Voting (MV)K=8, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1253.3
Majority Voting (MV)K=8, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1252.9
THINKMERGE (Ours (D))K=2, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1252.6
Majority Voting (MV)K=8, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1252.5
Majority Voting (MV)K=8, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1252.5
THINKMERGE (Ours (C))K=4, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1252.4
THINKMERGE (DirectMerge (A))K=4, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1252.2
THINKMERGE (Trimming (B))K=4, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1252.2
Majority Voting (MV)K=2, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1252
THINKMERGE (Ours (D))K=4, Backbone=Qwen3-4B, Strategy=Shortest-K Merge2025.1251.8
THINKMERGE (DirectMerge (A))K=8, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1251.6
Majority Voting (MV)K=4, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1251.4
THINKMERGE (Trimming (B))K=8, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1251.3
THINKMERGE (Ours (C))K=8, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1251.3
Majority Voting (MV)K=4, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1251.2
THINKMERGE (DirectMerge (A))K=2, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1250.3
THINKMERGE (Ours (C))K=2, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1250.3
Majority Voting (MV)K=4, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1250.3
Majority Voting (MV)K=4, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1250.3
Majority Voting (MV)K=4, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1250.2
THINKMERGE (Ours (C))K=8, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1250.2
THINKMERGE (Trimming (B))K=2, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1250
THINKMERGE (DirectMerge (A))K=8, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1250
THINKMERGE (Trimming (B))K=8, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1250
Majority Voting (MV)K=2, Backbone=Qwen3-4B, Strategy=Early-Ready2025.1249.4
Majority Voting (MV)K=2, Backbone=Qwen3-4B, Strategy=All-Reduce2025.1249.2
THINKMERGE (DirectMerge (A))K=2, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1249.2
THINKMERGE (Trimming (B))K=2, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1249.2
THINKMERGE (Ours (C))K=2, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1249
THINKMERGE (Trimming (B))K=4, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1249
THINKMERGE (DirectMerge (A))K=4, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1248.9
THINKMERGE (Ours (C))K=4, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1248.9
Majority Voting (MV)K=2, Backbone=R1-Distill-Qwen-7B, Strategy=Early-Ready2025.1247.4
THINKMERGE (Ours (D))K=4, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1247.4
THINKMERGE (Ours (D))K=8, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1247.2
Majority Voting (MV)K=2, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1247.1
Majority Voting (MV)K=2, Backbone=R1-Distill-Qwen-7B, Strategy=All-Reduce2025.1244.9
THINKMERGE (Ours (D))K=2, Backbone=R1-Distill-Qwen-7B, Strategy=Shortest-K Merge2025.1243.8