| OpenMath-CodeLlama-13B (w/ code) |
- Accuracy
- 45.5
- Parameters (Billions)
- 13
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code) |
- Accuracy
- 45.5
- Parameters (Billions)
- 7
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
2024-06-18 |
코드 1 |
| DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code) |
- Accuracy
- 45.3
- Parameters (Billions)
- 8
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
2024-06-18 |
코드 1 |
| MathCoder-CL-34B |
- Accuracy
- 45.2
- Parameters (Billions)
- 34
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2023-10-05 |
코드 1 |
| MathCoder-L-34B |
- Accuracy
- 45.1
- Parameters (Billions)
- 34
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2023-10-05 |
코드 1 |
| MMIQC-72B |
- Accuracy
- 45.0
- Parameters (Billions)
- 72
|
Augmenting Math Word Problems via Iterative Question Composing
2024-01-17 |
코드 1 |
| ToRA-Code 7B (w/ code) |
- Accuracy
- 44.6
- Parameters (Billions)
- 7
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2023-09-29 |
코드 1 |
| OpenMath-Mistral-7B (w/ code) |
- Accuracy
- 44.5
- Parameters (Billions)
- 7
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| MMOS-CODE-7B(0-shot) |
- Accuracy
- 44.3
- Parameters (Billions)
- 7
|
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
2024-02-23 |
코드 1 |
| OpenMath-CodeLlama-7B (w/ code) |
- Accuracy
- 43.6
- Parameters (Billions)
- 7
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256) |
- Accuracy
- 43.5
- Parameters (Billions)
- 7
|
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
2023-12-14 |
코드 1 · 코드 2 · 코드 3 |
| DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code) |
- Accuracy
- 43.5
- Parameters (Billions)
- 7
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
2024-06-18 |
코드 1 |
| Minerva 62B (maj1@k, k=64) |
- Accuracy
- 43.4
- Parameters (Billions)
- 62
|
Solving Quantitative Reasoning Problems with Language Models
2022-06-29 |
코드 1 |
| ToRA 13B (w/ code) |
- Accuracy
- 43.0
- Parameters (Billions)
- 13
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2023-09-29 |
코드 1 |
| GPT-4 |
- Accuracy
- 42.5
|
Sparks of Artificial General Intelligence: Early experiments with GPT-4
2023-03-22 |
코드 1 · 코드 2 · 코드 3 |
| SFT-Mistral-7B |
- Accuracy
- 41.8
- Parameters (Billions)
- 7
|
연결 없음
논문 날짜 미기재 |
연결 없음 |
| Llama2-13B-KPMath-Plus |
- Accuracy
- 41
- Parameters (Billions)
- 13
|
Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
2024-03-04 |
연결 없음 |
| ToRA 7B (w/ code) |
- Accuracy
- 40.1
- Parameters (Billions)
- 7
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2023-09-29 |
코드 1 |
| MathCoder-CL-13B |
- Accuracy
- 35.9
- Parameters (Billions)
- 13
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2023-10-05 |
코드 1 |
| MuggleMATH-70B |
- Accuracy
- 35.6
- Parameters (Billions)
- 70
|
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
2023-10-09 |
코드 1 |
| PaLM 2 (few-shot, k=4, CoT) |
- Accuracy
- 34.3
|
PaLM 2 Technical Report
2023-05-17 |
코드 1 |
| Minerva 540B |
- Accuracy
- 33.6
- Parameters (Billions)
- 540
|
Solving Quantitative Reasoning Problems with Language Models
2022-06-29 |
코드 1 |
| Minerva 540B (5-shot) mCoT |
- Accuracy
- 33.6
- Parameters (Billions)
- 540
|
Galactica: A Large Language Model for Science
2022-11-16 |
코드 1 |
| Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL) |
- Accuracy
- 33.0
- Parameters (Billions)
- 7
|
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
2023-12-14 |
코드 1 · 코드 2 · 코드 3 |
| WizardMath-7B-V1.1 |
- Accuracy
- 33.0
- Parameters (Billions)
- 7
|
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
2023-08-18 |
코드 1 |
| Gemini Pro (4-shot) |
- Accuracy
- 32.6
|
Gemini: A Family of Highly Capable Multimodal Models
2023-12-19 |
코드 1 |
| MuggleMATH-13B |
- Accuracy
- 30.7
- Parameters (Billions)
- 13
|
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
2023-10-09 |
코드 1 |
| MathCoder-CL-7B |
- Accuracy
- 30.2
- Parameters (Billions)
- 7
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2023-10-05 |
코드 1 |
| MathCoder-L-13B |
- Accuracy
- 29.9
- Parameters (Billions)
- 13
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2023-10-05 |
코드 1 |
| Qwen2idae-16x14B (4-shot) |
- Accuracy
- 29.9
|
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
2024-01-05 |
코드 1 · 코드 2 |