List your company

General Reasoning on AGIEval

70.4Exact MatchGPT-4
27.44838.59949.7560.901Nov 18, 2023Apr 1, 2024Aug 14, 2024Dec 27, 2024May 11, 2025Sep 23, 2025Feb 5, 2026

Evaluation results

MethodLinks
GPT-4Setting=Zero-shot2023.1170.4
Qwen 3 14Bshots=5-shot2026.0166.1
Ministral 3 14Bshots=5-shot2026.0164.8
Qwen 3 8Bshots=5-shot2026.0159.6
Ministral 3 8Bshots=5-shot2026.0159.1
Gemma 3 12Bshots=5-shot2026.0158.7
Qwen 3 4Bshots=5-shot2026.0157
ChatGPTSetting=Zero-shot2023.1153.13
Ministral 3 3Bshots=5-shot2026.0151.1
Orca 2-13BSetting=Zero-shot, System Message=Default2023.1149.93
WizardLM-70BSetting=Zero-shot2023.1148.73
Orca 2-13BSetting=Zero-shot, System Message=Cautious2023.1148.18
LLaMA-2-Chat-70BSetting=Zero-shot2023.1146.7
Engram-40BShots=0-shot2026.0145.9
Orca-1-13BSetting=Zero-shot2023.1145.69
Orca 2-7BSetting=Zero-shot, System Message=Default2023.1145.1
Orca 2-7BSetting=Zero-shot, System Message=Cautious2023.1143.97
Gemma 3 4Bshots=5-shot2026.0143
Engram-27BShots=0-shot2026.0141.8
LLaMA-2-Chat-13BSetting=Zero-shot2023.1138.85
OrthoMergeBase Model=Llama-3.1-8B, Fine-tuning Technique=OFT, Merging Strategy=OrthoMerge2026.0238.84
MoE-27BShots=0-shot2026.0138.6
TABase Model=Llama-3.1-8B, Fine-tuning Technique=OFT, Merging Strategy=TA2026.0238.53
DAREBase Model=Llama-3.1-8B, Fine-tuning Technique=OFT, Merging Strategy=DARE2026.0238.47
WizardLM-13BSetting=Zero-shot2023.1138.25
TABase Model=Llama-3.1-8B, Fine-tuning Technique=LoRA, Merging Strategy=TA2026.0237.9
DAREBase Model=Llama-3.1-8B, Fine-tuning Technique=LoRA, Merging Strategy=DARE2026.0237.86
TIESBase Model=Llama-3.1-8B, Fine-tuning Technique=OFT, Merging Strategy=TIES2026.0237.85
TIESBase Model=Llama-3.1-8B, Fine-tuning Technique=LoRA, Merging Strategy=TIES2026.0237.09
TSV-MBase Model=Llama-3.1-8B, Fine-tuning Technique=OFT, Merging Strategy=TSV-M2026.0236.96
Llama-3.1-8BBase Model=Llama-3.1-8B, Fine-tuning Technique=None, Merging Strategy=None2026.0235.76
TSV-MBase Model=Llama-3.1-8B, Fine-tuning Technique=LoRA, Merging Strategy=TSV-M2026.0234.51
Dense-4BShots=0-shot2026.0129.1