Our new X account is live! Follow @wizwand_team for updates

Dialogue on MT-Bench (test)

8.36GPT-4 Score

LoRA

Updated 4d ago

Evaluation Results

Method	Links
LoRA 2025.12		8.36
FAA 2025.12		8.35
FF 2025.12		8.34
FourierFT 2025.12		8.33
AdapterH 2025.12		8.32
FF 2025.12		8.17
FF 2025.12		7.88
LoRA 2025.12		7.86
FAA 2025.12		7.82
FourierFT 2025.12		7.81
AdapterH 2025.12		7.78
AdapterH 2025.12		7.48
FAA 2025.12		7.45
FourierFT 2025.12		7.41
LoRA 2025.12		7.4
GRPO + R2M 2026.01		7.3
RLOO + R2M 2026.01		7.3
GRPO + Pretrained RM 2026.01		7.1
RLOO 2026.01		7.1
RLOO + Pretrained RM 2026.01		7.1
ReMax 2026.01		7
GRPO 2026.01		7
GRPO + Iterative RMHead 2026.01		7
RLOO + Iterative RMHead 2026.01		7
SFT 2026.01		6.9
REINFORCE++ 2026.01		6.8
RLOO + R2M 2026.01		6.7
GRPO + R2M w/o Train 2026.01		6.7
GRPO + R2M 2026.01		6.6
GRPO + Iterative RMHead 2026.01		6.5
RLOO + Pretrained RM 2026.01		6.5
RLOO + Iterative RMHead 2026.01		6.5
RLOO + R2M w/o Train 2026.01		6.5
SFT 2026.01		6.4
ReMax 2026.01		6.4
GRPO + Pretrained RM 2026.01		6.4
RLOO 2026.01		6.4
REINFORCE++ 2026.01		6.3
GRPO 2026.01		6.3
GRPO + R2M w/o Train 2026.01		6.2
RLOO + R2M w/o Train 2026.01		6.2
FAA 2025.12		5.24
AdapterH 2025.12		5.23
LoRA 2025.12		5.22
FourierFT 2025.12		5.21
FF 2025.12		5.19