context listlengths 1 1 | gen_kwargs dict | repeat_idx int64 0 9 | request_idx int64 0 12k | task_name stringclasses 13
values | metadata dict | model_outputs stringlengths 379 206k |
|---|---|---|---|---|---|---|
[
{
"content": "The following are multiple choice questions (with answers) about history. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nThis question refers to the following information.\nIn Russia there was nothing going on well,... | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 4,640 | MMLUPro | {
"expected_answer": "",
"problem_id": "",
"reference_rationale": null,
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, let's tackle these questions one by one. Starting with the first one about the Russian text. The question is asking which movement had a direct concern for the welfare of the working classes, specifically mentioning the idea of national liberation and the focus on the working class. From what I remember, ... |
[
{
"content": "The following are multiple choice questions (with answers) about health. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nWhich of the following is the body cavity that contains the pituitary gland?\nOptions:\nA. Vent... | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 6,453 | MMLUPro | {
"expected_answer": "",
"problem_id": "",
"reference_rationale": null,
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, let's tackle this question. So, the patient is a 37-year-old man with cocaine dependency. He's been trying to abstain but lives in an area with heavy drug sales. He doesn't like his hospital outpatient group but likes Cocaine Anonymous. His vital signs are normal: temperature 37°C (which is 98.6°F, so tha... |
[
{
"content": "\"You are a coding expert. Given a competition-level coding problem, you need to write a Python program to solve it. You may start by outlining your thought process. In the end, please provide the complete code in a code block enclosed with ``` ```. The code should take stdin as input and print th... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 2,
"temperature": 0.7
} | 2 | 189 | CodeElo | {
"expected_answer": "",
"problem_id": "",
"reference_rationale": null,
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, let's try to understand this problem. So, the problem is about eliminating balls with merging. We have to compute f(i) for each i from x to n (and x is 1 here). The function f(i) counts the number of j's such that after performing the merging operations exactly i-1 times on the first i balls, we end up wi... |
[
{
"content": "The following are multiple choice questions (with answers) about economics. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nFor a stationary autoregressive process, shocks will\nOptions:\nA. Never occur\nB. Persist i... | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 7,125 | MMLUPro | {
"expected_answer": "",
"problem_id": "",
"reference_rationale": null,
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, let's tackle these questions one by one. I need to make sure I understand each concept before answering. Let's start with the first question about stationary autoregressive processes.
The question asks which option correctly describes what happens to shocks in a stationary AR process. From what I remembe... |
[
{
"content": "The following are multiple choice questions (with answers) about physics. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nSay the pupil of your eye has a diameter of 5 mm and you have a telescope with an aperture of ... | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 9,792 | MMLUPro | {
"expected_answer": "",
"problem_id": "",
"reference_rationale": null,
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, let's tackle these physics questions one by one. I need to make sure I understand each problem and figure out the correct answers. Let's start with the first one.
**Question 1:**
The pupil of the eye has a diameter of 5 mm, and the telescope has an aperture of 50 cm. How much more light can the telescope... |
[{"content":"Your response should be in the following format:\nAnswer: {your chosen multiple choice (...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 1,
"temperature": 0.7
} | 1 | 35 | HLESubset | {"expected_answer":"E","problem_id":"66eaf1f49c43656de6cf31f6","reference_rationale":"torque is enou(...TRUNCATED) | "<think>\nOkay, let's try to figure out how close the robot's finger can get to the shoulder when th(...TRUNCATED) |
[{"content":"The following are multiple choice questions (with answers) about math. Think step by st(...TRUNCATED) | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 7,645 | MMLUPro | {"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED) | "<think>\nOkay, let's tackle these questions one by one. Starting with the first one about the symme(...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 178 | LiveCodeBenchV5 | {"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED) | "<think>\nOkay, I need to solve this problem where I have to find the maximum possible total score b(...TRUNCATED) |
[{"content":"The following are multiple choice questions (with answers) about philosophy. Think step(...TRUNCATED) | {
"do_sample": null,
"max_new_tokens": 2048,
"seed": 0,
"temperature": 0
} | 0 | 10,927 | MMLUPro | {"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED) | "<think>\nOkay, let's tackle these questions one by one. Starting with the first one about the symbo(...TRUNCATED) |
[{"content":"In this problem, multiple options can be correct. Give a detailed solution and end the (...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 3 | JEEBench | {"expected_answer":"CD","problem_id":"8","reference_rationale":null,"reference_solution":null,"subje(...TRUNCATED) | "<think>\nOkay, let's tackle this physics problem. So, the question is about an incandescent bulb's (...TRUNCATED) |
End of preview. Expand in Data Studio
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
mlfoundations-dev/AceReason-Nemotron-1.1-7B_eval_5554
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces | AIME25 | HLE | LiveCodeBenchv5 | HMMT |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 72.3 | 93.5 | 91.2 | 27.7 | 75.2 | 55.6 | 36.1 | 39.9 | 37.2 | 60.7 | 12.9 | 55.9 | 43.0 |
AIME24
- Average Accuracy: 72.33% ± 1.34%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 73.33% | 22 | 30 |
| 2 | 63.33% | 19 | 30 |
| 3 | 73.33% | 22 | 30 |
| 4 | 66.67% | 20 | 30 |
| 5 | 76.67% | 23 | 30 |
| 6 | 73.33% | 22 | 30 |
| 7 | 76.67% | 23 | 30 |
| 8 | 73.33% | 22 | 30 |
| 9 | 76.67% | 23 | 30 |
| 10 | 70.00% | 21 | 30 |
AMC23
- Average Accuracy: 93.50% ± 0.81%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 92.50% | 37 | 40 |
| 2 | 97.50% | 39 | 40 |
| 3 | 97.50% | 39 | 40 |
| 4 | 95.00% | 38 | 40 |
| 5 | 92.50% | 37 | 40 |
| 6 | 92.50% | 37 | 40 |
| 7 | 90.00% | 36 | 40 |
| 8 | 90.00% | 36 | 40 |
| 9 | 95.00% | 38 | 40 |
| 10 | 92.50% | 37 | 40 |
MATH500
- Accuracy: 91.20%
Accuracy Questions Solved Total Questions 91.20% 456 500
MMLUPro
- Accuracy: 27.70%
Accuracy Questions Solved Total Questions 27.70% N/A N/A
JEEBench
- Average Accuracy: 75.21% ± 0.30%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 75.15% | 387.0 | 515 |
| 2 | 75.87% | 390.75 | 515 |
| 3 | 74.61% | 384.25 | 515 |
GPQADiamond
- Average Accuracy: 55.56% ± 1.33%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 53.03% | 105 | 198 |
| 2 | 55.05% | 109 | 198 |
| 3 | 58.59% | 116 | 198 |
LiveCodeBench
- Average Accuracy: 36.07% ± 16.14%
- Number of Runs: 6
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 73.97% | 378 | 511 |
| 2 | 70.65% | 361 | 511 |
| 3 | 71.82% | 367 | 511 |
| 4 | 0.00% | 0 | 511 |
| 5 | 0.00% | 0 | 511 |
| 6 | 0.00% | 0 | 511 |
CodeElo
- Average Accuracy: 39.90% ± 0.39%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 40.66% | 159 | 391 |
| 2 | 39.39% | 154 | 391 |
| 3 | 39.64% | 155 | 391 |
CodeForces
- Average Accuracy: 37.23% ± 0.32%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 37.75% | 171 | 453 |
| 2 | 36.64% | 166 | 453 |
| 3 | 37.31% | 169 | 453 |
AIME25
- Average Accuracy: 60.67% ± 1.99%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 56.67% | 17 | 30 |
| 2 | 63.33% | 19 | 30 |
| 3 | 50.00% | 15 | 30 |
| 4 | 56.67% | 17 | 30 |
| 5 | 56.67% | 17 | 30 |
| 6 | 60.00% | 18 | 30 |
| 7 | 66.67% | 20 | 30 |
| 8 | 70.00% | 21 | 30 |
| 9 | 56.67% | 17 | 30 |
| 10 | 70.00% | 21 | 30 |
HLE
- Average Accuracy: 12.87% ± 0.64%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 12.87% | 66 | 513 |
| 2 | 14.23% | 73 | 513 |
| 3 | 11.50% | 59 | 513 |
LiveCodeBenchv5
- Average Accuracy: 55.92% ± 1.18%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 54.47% | 201 | 369 |
| 2 | 55.01% | 203 | 369 |
| 3 | 58.27% | 215 | 369 |
HMMT
- Average Accuracy: 43.00% ± 1.45%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 50.00% | 15 | 30 |
| 2 | 43.33% | 13 | 30 |
| 3 | 36.67% | 11 | 30 |
| 4 | 36.67% | 11 | 30 |
| 5 | 40.00% | 12 | 30 |
| 6 | 40.00% | 12 | 30 |
| 7 | 43.33% | 13 | 30 |
| 8 | 50.00% | 15 | 30 |
| 9 | 43.33% | 13 | 30 |
| 10 | 46.67% | 14 | 30 |
- Downloads last month
- 2