| Gemini 2.0 Flash Experimental |
- Accuracy
- 89.7
|
연결 없음
논문 날짜 미기재 |
연결 없음 |
| Qwen2.5-Math-72B-Instruct(TIR,Greedy) |
- Accuracy
- 88.1
- Parameters (Billions)
- 72
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| GPT-4 Turbo (MACM, w/code, voting) |
- Accuracy
- 87.920
|
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
2024-04-06 |
코드 1 |
| Qwen2.5-Math-72B-Instruct(COT,Greedy) |
- Accuracy
- 85.9
- Parameters (Billions)
- 72
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| Qwen2.5-Math-7B-Instruct(TIR,Greedy) |
- Accuracy
- 85.2
- Parameters (Billions)
- 7
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| GPT-4-code model (CSV, w/ code, SC, k=16) |
- Accuracy
- 84.3
|
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
2023-08-15 |
코드 1 |
| Qwen2-Math-72B-Instruct(greedy) |
- Accuracy
- 84.0
- Parameters (Billions)
- 72
|
Qwen2 Technical Report
2024-07-15 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 |
| Qwen2.5-Math-7B-Instruct(COT,Greedy) |
- Accuracy
- 83.6
- Parameters (Billions)
- 7
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| Qwen2.5-Math-1.5B-Instruct(TIR,Greedy) |
- Accuracy
- 79.9
- Parameters (Billions)
- 1.5
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| OpenMath2-Llama3.1-70B (majority@256) |
- Accuracy
- 79.6
|
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
2024-10-02 |
코드 1 |
| OpenMath2-Llama3.1-8B (majority@256) |
- Accuracy
- 76.1
|
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
2024-10-02 |
코드 1 |
| Qwen2.5-Math-1.5B-Instruct(COT,Greedy) |
- Accuracy
- 75.8
- Parameters (Billions)
- 1.5
|
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
2024-09-18 |
연결 없음 |
| GPT-4-code model (CSV, w/ code) |
- Accuracy
- 73.5
|
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
2023-08-15 |
코드 1 |
| CR (GPT-4-turbo model, w/ code) |
- Accuracy
- 72.2
|
Cumulative Reasoning with Large Language Models
2023-08-08 |
코드 1 |
| OpenMath2-Llama3.1-70B |
- Accuracy
- 71.9
|
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
2024-10-02 |
코드 1 |
| LogicNet (with code interpreter) |
- Accuracy
- 71.2
|
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
2023-08-15 |
코드 1 |
| Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code) |
- Accuracy
- 70.8
|
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
2024-06-26 |
코드 1 |
| GPT-4-code model (w/ code) |
- Accuracy
- 69.7
|
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
2023-08-15 |
코드 1 |
| OpenMath2-Llama3.1-8B |
- Accuracy
- 67.8
|
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
2024-10-02 |
코드 1 |
| AlphaMath-7B-SBS@3 |
- Accuracy
- 66.3
|
AlphaMath Almost Zero: Process Supervision without Process
2024-05-06 |
코드 1 |
| Minerva 62B (maj5@256) |
- Accuracy
- 64.9
- Parameters (Billions)
- 62
|
Solving Quantitative Reasoning Problems with Language Models
2022-06-29 |
코드 1 |
| DAMOMath-7B |
- Accuracy
- 64.5
- Parameters (Billions)
- 7
|
연결 없음
논문 날짜 미기재 |
연결 없음 |
| MMOS-DeepSeekMath-7B(0-shot,k=50) |
- Accuracy
- 63.7
- Parameters (Billions)
- 7
|
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
2024-02-23 |
코드 1 |
| GPT-4-code model (w/o code) |
- Accuracy
- 60.8
|
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
2023-08-15 |
코드 1 |
| OpenMath-CodeLlama-70B (w/ code, SC, k=50) |
- Accuracy
- 60.4
- Parameters (Billions)
- 70
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| OpenMath-CodeLlama-34B (w/ code, SC, k=50) |
- Accuracy
- 60.2
- Parameters (Billions)
- 34
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| ToRA-Code 34B model (w/ code, SC, k=50) |
- Accuracy
- 60.0
- Parameters (Billions)
- 34
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
2023-09-29 |
코드 1 |
| DeepSeekMATH-RL-7B (w/ code, greedy decoding) |
- Accuracy
- 58.8
- Parameters (Billions)
- 7
|
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
2024-02-05 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| OpenMath-Llama2-70B (w/ code, SC, k=50) |
- Accuracy
- 58.3
- Parameters (Billions)
- 70
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
2024-02-15 |
코드 1 |
| CR (GPT-4 model, w/o code) |
- Accuracy
- 58.0
|
Cumulative Reasoning with Large Language Models
2023-08-08 |
코드 1 |