Dataset Viewer
Auto-converted to Parquet Duplicate
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
669
302k
[ { "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 need to make sure I understand each context and then pick the correct answer based on the information given. Let's start with the first one. **First Question:** The passage is from Zola's text about the working classes and their concerns. The question is asking ...
[ { "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 need to make sure I understand each question and then figure out the correct answer based on my knowledge. Let's start with the first one. **First Question:** Which body cavity contains the pituitary gland? Hmm, the pituitary gland is part of the endocrine syst...
[ { "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, so I need to solve this problem where I have to compute f(i) for each i from x to n. Let me try to understand the problem again. The problem says that for each i, f(i) is the number of integers j such that after performing exactly i-1 operations, we end up with a set S containing just {j}. The operation...
[ { "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 and then choose the correct answer. Let's start with the first one. **First Question: Stationary Autoregressive Process and Shocks** The question is about what happens to shocks in a stationary autoregressive process. The opt...
[ { "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 go through each one carefully and make sure I understand the concepts before jumping to the answers. Let's start with the first question. **First Question:** The pupil of the eye is 5 mm, and the telescope has an aperture of 50 cm. How much more ...
[{"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 need to figure out how close the robot's finger can get to its shoulder when fol(...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 need to go through each problem carefully (...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 total score by jumping (...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 need to make sure I understand each one an(...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, so I have this problem about an incandescent bulb and its filament. Let me try to thi(...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_herorun_ckpt05000_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 59.7 92.0 89.0 27.3 61.7 49.8 56.9 23.9 26.4 11.4 30.7 50.0 44.3

AIME24

  • Average Accuracy: 59.67% ± 1.29%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 53.33% 16 30
2 60.00% 18 30
3 60.00% 18 30
4 60.00% 18 30
5 53.33% 16 30
6 63.33% 19 30
7 66.67% 20 30
8 63.33% 19 30
9 56.67% 17 30
10 60.00% 18 30

AMC23

  • Average Accuracy: 92.00% ± 0.85%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 90.00% 36 40
2 92.50% 37 40
3 90.00% 36 40
4 92.50% 37 40
5 97.50% 39 40
6 92.50% 37 40
7 87.50% 35 40
8 92.50% 37 40
9 95.00% 38 40
10 90.00% 36 40

MATH500

  • Accuracy: 89.00%
    Accuracy Questions Solved Total Questions
    89.00% 445 500

MMLUPro

  • Accuracy: 27.33%
    Accuracy Questions Solved Total Questions
    27.33% N/A N/A

JEEBench

  • Average Accuracy: 61.67% ± 0.80%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 62.77% 323.25 515
2 62.52% 322.0 515
3 59.71% 307.5 515

GPQADiamond

  • Average Accuracy: 49.83% ± 1.40%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 46.46% 92 198
2 51.01% 101 198
3 52.02% 103 198

LiveCodeBench

  • Average Accuracy: 56.88% ± 1.21%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 55.77% 285 511
2 59.30% 303 511
3 55.58% 284 511

CodeElo

  • Average Accuracy: 23.87% ± 0.76%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 22.76% 89 391
2 25.32% 99 391
3 23.53% 92 391

CodeForces

  • Average Accuracy: 26.42% ± 0.57%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 26.49% 120 453
2 25.39% 115 453
3 27.37% 124 453

HLE

  • Average Accuracy: 11.39% ± 0.51%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 11.33% 58 512
2 12.50% 64 512
3 10.35% 53 512

HMMT

  • Average Accuracy: 30.67% ± 1.40%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 23.33% 7 30
2 33.33% 10 30
3 33.33% 10 30
4 36.67% 11 30
5 33.33% 10 30
6 33.33% 10 30
7 26.67% 8 30
8 23.33% 7 30
9 30.00% 9 30
10 33.33% 10 30

AIME25

  • Average Accuracy: 50.00% ± 2.11%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 15 30
2 53.33% 16 30
3 43.33% 13 30
4 43.33% 13 30
5 60.00% 18 30
6 40.00% 12 30
7 56.67% 17 30
8 56.67% 17 30
9 53.33% 16 30
10 43.33% 13 30

LiveCodeBenchv5

  • Average Accuracy: 44.26% ± 0.59%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 44.72% 165 369
2 44.99% 166 369
3 43.09% 159 369
Downloads last month
5