Share your thoughts, 1 month free Claude Pro on usSee more

Arithmetic Reasoning on AddSub

99Accuracy

CLoT

Updated 8d ago

Evaluation Results

Method
CLoT 2026.04	99	-	-
CLoT 2026.04	99	-	-
CLoT 2026.04	99	-	-
CoT-SC 2026.04	98.5	-	-
CoT-SC 2026.04	98.4	-	-
C-CoT 2026.04	98.4	-	-
Teaching-Inspired Integrated Prompting Framework 2024.10	98.2	-	-
Meta-Reasoning Paradigm 2023.06	98	-	-
CoT 2026.04	98	-	-
C-CoT 2026.04	97.9	-	-
ISP-CoT 2026.04	97.7	-	-
CoT 2026.04	97.7	-	-
Tr 2026.04	97.5	-	-
C-CoT 2026.04	97.2	-	-
CoT-SC 2026.04	96.1	-	-
ISP-CoT 2026.04	96.1	-	-
Automatic Model Selection with LLMs 2023.05	95.7	-	-
Previous SoTA 2024.10	95.7	-	-
CoT 2024.10	95.7	-	-
Meta-Reasoning Paradigm 2023.06	95.4	-	-
DUP 2024.04	95.1	-	-
PAL 2023.05	94.9	-	-
Relevance and LCA operation classifier 2022.03	94.9	-	-
CoT 2026.04	94.9	-	-
FourierMoE 2026.04	94.68	-	-
CoT 2023.05	93.9	-	-
Chain-of-Thought Paradigm 2023.06	93.9	-	-
AR 2026.04	93.9	-	-
8-shot CoT 2023.05	93.7	-	-
Self-consistency 2022.03	93.7	-	-
Zero-shot PS+ 2024.04	93.1	-	-
MELoRA 2026.04	92.91	-	-
Teaching-Inspired Integrated Prompting Framework 2024.10	92.7	-	-
DoRA 2026.04	92.41	-	-
HydraLoRA 2026.04	92.41	-	-
Zero-shot CoT 2024.04	92.4	-	-
DUP 2024.04	92.1	-	-
Least-to-Most 2024.04	92.1	-	-
PAL 2023.05	91.9	-	-
CoT-prompting 2022.03	91.9	-	-
LoRA 2026.04	91.9	-	-
Automatic Model Selection with LLMs 2023.05	91.6	-	-
Self-consistency 2022.03	91.6	-	-
Chain-of-Thought Paradigm 2023.06	91.6	-	-
TopLoRA 2026.04	91.31	-	-
Least-to-Most 2024.04	91.3	-	-
Automatic Model Selection with LLMs 2023.05	90.6	-	-
Manual-CoT 2024.04	90.6	-	-
CoT 2023.05	90.4	-	-
COSP 2023.05	89.9	-	-
Auto-CoT 2024.04	89.9	-	-
CoT 2024.10	89.6	-	-
PAL 2023.05	89.4	-	-
CoT-prompting 2022.03	89.4	-	-
Auto-CoT 2023.05	89.1	-	-
0-shot CoT 2023.05	88.9	-	-
CoT 2023.05	88.4	-	-
FourierMoE 2026.04	87.85	-	-
AR 2026.04	87.1	-	-
5-shot CoT 2023.05	86.6	-	-
Meta-Reasoning Paradigm 2023.06	86.6	-	-
Zero-shot PS+ 2024.04	86.5	-	-
HydraLoRA 2026.04	86.08	-	-
DoRA 2026.04	85.95	-	-
MELoRA 2026.04	85.82	-	-
Zero-shot CoT 2024.04	85.8	-	-
Chain-of-Thought Paradigm 2023.06	85.5	-	-
Chain-of-Thought Paradigm 2023.06	85.3	-	-
Auto-CoT 2022.10	84.8	-	-
LoRA 2026.04	84.56	-	-
State-of-the-Art 2023.06	84	-	-
Few-Shot 2022.10	83.3	-	-
Standard Prompting Paradigm 2023.06	83.3	-	-
AR 2026.04	82.3	-	-
Manual-CoT 2022.10	81.3	-	-
Chain-of-Thought Paradigm 2023.06	81.3	-	-
COSP 2023.05	78.9	-	-
Zero-Shot 2022.10	77	-	-
Standard Prompting Paradigm 2023.06	77	-	-
Zero-Shot-CoT 2022.10	74.7	-	-
Chain-of-Thought Paradigm 2023.06	74.7	-	-
Auto-CoT 2023.05	73.2	-	-
5-shot CoT 2023.05	72.4	-	-
Zero-shot 2023.12	70.13	-	-
CoT-Influx 2023.12	69.62	-	-
0-shot CoT 2023.05	69.1	-	-
Prev 8-shot CoT 2023.05	67.8	-	-
Self-consistency 2022.03	67.8	-	-
DoRA 2026.04	67.09	-	-
GRASS 2026.04	67.09	-	-
FFT 2026.04	66.84	-	-
LoRA 2026.04	66.84	-	-
GRASS 2026.04	66.33	-	-
FFT 2026.04	66.08	-	-
Few-shot-CoT 2023.12	65.82	-	-
LoRA 2026.04	65.06	-	-
Self-consistency 2022.03	63.5	-	-
5-shot CoT 2023.05	63.3	-	-
LoRA 2026.04	63.04	-	-
DoRA 2026.04	63.03	-	-

Showing 100 of 125 rows