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 38 241k |
|---|---|---|---|---|---|---|
[
{
"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. I'll start with the first one about the passage from Emile Zola's Germinal. The question is asking which movement the concern for the working classes in the passage is typically part of. The passage talks about Souvarine being in despair because the Nihilists are f... |
[
{
"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 these questions one by one. I'll start with the first question: "Which of the following is the body cavity that contains the pituitary gland?"
Hmm, I remember from my anatomy class that the pituitary gland is located at the base of the brain. I think it's in the cranial cavity. So the optio... |
[
{
"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 see. I need to solve this problem called "Eliminating Balls With Merging (Hard Version)". The problem is about figuring out the number f(i) for each i from x to n, where f(i) is the count of j such that you can reach the set {j} after exactly i-1 operations. The operations involve choosing l < curre... |
[
{
"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 economics questions one by one. I'll go through each step by step and try to figure out the correct answers.
Starting with the first question about stationary autoregressive processes. The question asks what happens to shocks in such a process. From what I remember, a stationary AR pr... |
[
{
"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 questions one by one. I'll go through each step by step and try to figure out the answers.
Starting with the first question:
**Question 1:**
Say the pupil of your eye has a diameter of 5 mm and you have a telescope with an aperture of 50 cm. How much more light can the telescope ga... |
[{"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> Okay, so I have this problem about a robot arm with four segments, each with a revolute joi(...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> Okay, let's tackle these questions one by one. I'll go through each step by step and try to(...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> Okay, I need to solve this problem where I have to find the maximum possible score when jum(...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> Okay, let's tackle these questions one by one. I'll go through each step by step and try to(...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> Okay, let's tackle this problem step by step. So, the question is about an incandescent bul(...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/openthoughts3_10k_llama3_eval_5554
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces | HLE | HMMT | AIME25 | LiveCodeBenchv5 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 14.0 | 56.0 | 73.4 | 14.4 | 32.4 | 46.1 | 27.2 | 7.3 | 10.7 | 11.4 | 12.0 | 18.7 | 19.9 |
AIME24
- Average Accuracy: 14.00% ± 0.79%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 10.00% | 3 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 16.67% | 5 | 30 |
| 6 | 13.33% | 4 | 30 |
| 7 | 16.67% | 5 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 13.33% | 4 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 56.00% ± 1.13%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 55.00% | 22 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 55.00% | 22 | 40 |
| 4 | 57.50% | 23 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 62.50% | 25 | 40 |
| 7 | 57.50% | 23 | 40 |
| 8 | 57.50% | 23 | 40 |
| 9 | 55.00% | 22 | 40 |
| 10 | 47.50% | 19 | 40 |
MATH500
- Accuracy: 73.40%
Accuracy Questions Solved Total Questions 73.40% 367 500
MMLUPro
- Accuracy: 14.41%
Accuracy Questions Solved Total Questions 14.41% N/A N/A
JEEBench
- Average Accuracy: 32.38% ± 0.26%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 32.09% | 165.25 | 515 |
| 2 | 33.01% | 170.0 | 515 |
| 3 | 32.04% | 165.0 | 515 |
GPQADiamond
- Average Accuracy: 46.13% ± 0.50%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 44.95% | 89 | 198 |
| 2 | 46.46% | 92 | 198 |
| 3 | 46.97% | 93 | 198 |
LiveCodeBench
- Average Accuracy: 27.20% ± 1.11%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 25.05% | 128 | 511 |
| 2 | 28.77% | 147 | 511 |
| 3 | 27.79% | 142 | 511 |
CodeElo
- Average Accuracy: 7.33% ± 0.87%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 8.44% | 33 | 391 |
| 2 | 7.93% | 31 | 391 |
| 3 | 5.63% | 22 | 391 |
CodeForces
- Average Accuracy: 10.74% ± 0.45%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 11.48% | 52 | 453 |
| 2 | 10.82% | 49 | 453 |
| 3 | 9.93% | 45 | 453 |
HLE
- Average Accuracy: 11.44% ± 1.15%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 11.50% | 59 | 513 |
| 2 | 13.84% | 71 | 513 |
| 3 | 8.97% | 46 | 513 |
HMMT
- Average Accuracy: 12.00% ± 1.43%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 10.00% | 3 | 30 |
| 3 | 6.67% | 2 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 6.67% | 2 | 30 |
| 7 | 10.00% | 3 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 6.67% | 2 | 30 |
| 10 | 16.67% | 5 | 30 |
AIME25
- Average Accuracy: 18.67% ± 1.07%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.00% | 6 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 23.33% | 7 | 30 |
| 6 | 23.33% | 7 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 13.33% | 4 | 30 |
| 10 | 16.67% | 5 | 30 |
LiveCodeBenchv5
- Average Accuracy: 19.87% ± 0.77%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 19.24% | 71 | 369 |
| 2 | 21.41% | 79 | 369 |
| 3 | 18.97% | 70 | 369 |
- Downloads last month
- 3