← Arithmetic Reasoning
평가 기록
과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.
표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.
| 모델 | 원본 지표·값 | 논문 | 구현 |
|---|---|---|---|
| OpenMath-CodeLlama-34B (w/ code, SC, k=50) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| Claude 2 (0-shot chain-of-thought) |
|
Model Card and Evaluations for Claude Models 2023-07-11 |
연결 없음 |
| Shivaay-4B (8-shot chain-of-thought) |
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| DeepMind 70B Model (SFT+ORM-RL, ORM reranking) |
|
Solving math word problems with process- and outcome-based feedback 2022-11-25 |
연결 없음 |
| MMOS-DeepSeekMath-7B(0-shot,k=50) |
|
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning 2024-02-23 |
코드 1 |
| DeepMind 70B Model (SFT+PRM-RL, PRM reranking) |
|
Solving math word problems with process- and outcome-based feedback 2022-11-25 |
연결 없음 |
| GPT-4 |
|
Sparks of Artificial General Intelligence: Early experiments with GPT-4 2023-03-22 |
코드 1 · 코드 2 · 코드 3 |
| OpenMath-Mistral-7B (w/ code, SC, k=50) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| Orca-Math 7B (fine-tuned) |
|
Orca-Math: Unlocking the potential of SLMs in Grade School Math 2024-02-16 |
연결 없음 |
| DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code) |
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving 2024-06-18 |
코드 1 |
| OpenMath-CodeLlama-13B (w/ code, SC, k=50) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| Gemini Pro (maj1@32) |
|
Gemini: A Family of Highly Capable Multimodal Models 2023-12-19 |
코드 1 |
| Codex (Self-Evaluation Guided Decoding, PAL, multiple reasoning chains, 9-shot gen, 5-shot eval) |
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| Claude 1.3 (0-shot chain-of-thought) |
|
Model Card and Evaluations for Claude Models 2023-07-11 |
연결 없음 |
| ToRA-Code-34B (SC, k=50) |
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving 2023-09-29 |
코드 1 |
| OpenMath-CodeLlama-7B (w/ code, SC, k=50) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| OVM-Mistral-7B (verify100@1) |
|
OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning 2023-11-16 |
코드 1 |
| OpenMath-Llama2-70B (w/ code) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| OpenMath-CodeLlama-70B (w/ code) |
|
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 2024-02-15 |
코드 1 |
| code-davinci-002 175B (LEVER, 8-shot) |
|
LEVER: Learning to Verify Language-to-Code Generation with Execution 2023-02-16 |
코드 1 |
| ToRA 70B |
|
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving 2023-09-29 |
코드 1 |
| Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL) |
|
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations 2023-12-14 |
코드 1 · 코드 2 · 코드 3 |
| MathCoder-L-70B |
|
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning 2023-10-05 |
코드 1 |
| WizardMath-7B-V1.1 |
|
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct 2023-08-18 |
코드 1 |
| DIVERSE 175B (8-shot) |
|
Making Large Language Models Better Reasoners with Step-Aware Verifier 2022-06-06 |
연결 없음 |
| OVM-Mistral-7B (verify20@1) |
|
OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning 2023-11-16 |
코드 1 |
| DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code) |
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving 2024-06-18 |
코드 1 |
| ChatGPT (Ask, Refine, Trust) |
|
The ART of LLM Refinement: Ask, Refine, and Trust 2023-11-14 |
연결 없음 |
| DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code) |
|
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving 2024-06-18 |
코드 1 |
| MetaMath 70B |
|
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models 2023-09-21 |
코드 1 |