Datasets:
benchmark stringclasses 1
value | messages stringlengths 7.31k 182k | query stringclasses 30
values | model_response stringlengths 6.06k 142k | gold_answer null | lighteval_sha stringclasses 1
value | num_fewshot_seeds int64 1 1 | max_samples null | job_id stringclasses 1
value | start_time float64 3.93M 3.93M | end_time float64 3.93M 3.93M | total_evaluation_time_secondes stringclasses 1
value | model_name stringclasses 1
value | model_sha stringclasses 1
value | model_dtype null | model_size int64 -1 -1 | generation_parameters_early_stopping null | generation_parameters_repetition_penalty null | generation_parameters_frequency_penalty null | generation_parameters_length_penalty null | generation_parameters_presence_penalty null | generation_parameters_max_new_tokens null | generation_parameters_min_new_tokens null | generation_parameters_seed null | generation_parameters_stop_tokens null | generation_parameters_temperature float64 0.6 0.6 | generation_parameters_top_k int64 20 20 | generation_parameters_min_p null | generation_parameters_top_p float64 0.95 0.95 | generation_parameters_truncate_prompt null | generation_parameters_request_timeout null | generation_parameters_response_format null | generation_parameters_extra_body null | math_pass@1:1_samples float64 0.73 0.73 | math_pass@1:1_samples_stderr float64 0.08 0.08 | math_pass@1:4_samples float64 0.77 0.77 | math_pass@1:4_samples_stderr float64 0.06 0.06 | math_pass@1:8_samples float64 0.79 0.79 | math_pass@1:8_samples_stderr float64 0.06 0.06 | math_pass@1:16_samples float64 0.79 0.79 | math_pass@1:16_samples_stderr float64 0.06 0.06 | math_pass@1:32_samples float64 0.79 0.79 | math_pass@1:32_samples_stderr float64 0.06 0.06 | math_pass@1:64_samples float64 0.78 0.78 | math_pass@1:64_samples_stderr float64 0.06 0.06 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
aime24 | [{"content": "/think", "role": "system"}, {"content": "Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expressi... | Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expression that solves the problem. Think step by step before an... | <think>
Okay, so I have this problem here: Let ω ≠ 1 be a 13th root of unity. Find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{2k}) is divided by 1000. Hmm, that sounds a bit intimidating at first, but let's break it down step by step.
First, I know that roots of unity often have nice properties th... | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | [{"content": "/think", "role": "system"}, {"content": "Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expressi... | Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expression that solves the problem. Think step by step before an... | <think>
Okay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{2k}) is divided by 1000, where ω is a 13th root of unity not equal to 1. Hmm, roots of unity often relate to cyclotomic polynomials, so maybe that's a direction to go. Let me start by understanding the problem step by step.
... | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | [{"content": "/think", "role": "system"}, {"content": "Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expressi... | Solve the following math problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\boxed{ANSWER}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expression that solves the problem. Think step by step before an... | <think>
Okay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{2k}) is divided by 1000, where ω is a 13th root of unity not equal to 1. Hmm, roots of unity often relate to cyclotomic polynomials, maybe I can use some properties of those here. Let me start by recalling some concepts.
Fi... | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I have this problem here: Let ω ≠ 1 be a 13th root of unity. Find the remainde(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I have this problem here: Let ω ≠ 1 be a 13th root of unity. Find the remainde(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 | |
aime24 | "[{\"content\": \"/think\", \"role\": \"system\"}, {\"content\": \"Solve the following math problem (...TRUNCATED) | "Solve the following math problem efficiently and clearly. The last line of your response should be(...TRUNCATED) | "<think>\nOkay, so I need to find the remainder when the product from k=0 to 12 of (2 - 2ω^k + ω^{(...TRUNCATED) | null | b191a94a4ff01a88d30fd101c719ac766b8ed198 | 1 | null | 0 | 3,926,926.502511 | 3,930,200.159821 | 3273.657310629729 | openai/qwen-235b-a22-thinking | null | -1 | null | null | null | null | null | null | null | null | null | 0.6 | 20 | null | 0.95 | null | null | null | null | 0.733333 | 0.082118 | 0.766667 | 0.05864 | 0.7875 | 0.059376 | 0.785417 | 0.05699 | 0.789583 | 0.058029 | 0.782292 | 0.058068 |
End of preview. Expand in Data Studio
Qwen3-235B-A22B Evaluation Results — Reformatted Dataset
This dataset is a reformatted copy of eval results for Qwen-235B-A22B-Thinking, originally produced by the Nous Hermes evaluation suite. Original source: huggingface.co/datasets/NousResearch/eval-Qwen3-235B-A22B-reasoning. Each sample from the raw eval outputs (samples.jsonl) has been combined with its corresponding benchmark metrics (metrics.json) into clean, self-contained Parquet tables.
What's included: 15 benchmarks — every eval from the original suite except creative-writing-v3 and eqbench3 (which had no sample-level conversation data and were omitted).
Key columns in each Parquet file:
messages— full conversation (system/user/assistant) as a JSON stringquery— the user's question or promptmodel_response— the model's raw generationgold_answer— ground truth (when available)model_name,temperature,top_k,top_p— generation config- All per-benchmark score columns (e.g.
math_pass@1:64_samples,eval_overall_winrate,extractive_match, etc.)
Excluded: creative-writing-v3, eqbench3
Summary
| Benchmark | Score | Metric | Samples | Overlong rate |
|---|---|---|---|---|
| aime24 | 0.782 | math_pass@1:64_samples | 64 | 0.5% |
| aime25 | 0.718 | math_pass@1:64_samples | 64 | 0.1% |
| arenahard | 0.939 | eval/overall_winrate | 500 | 0.0% |
| bbh_generative | 0.884 | extractive_match | 1 | 0.0% |
| drop_generative_nous | 0.903 | drop_acc | 1 | 0.0% |
| gpqa_diamond | 0.697 | gpqa_pass@1:8_samples | 8 | 0.1% |
| ifeval | 0.914 | inst_level_loose_acc | 1 | 0.0% |
| lcb-v6-aug2024+ | 0.651 | eval/pass_1 | 1 | 0.2% |
| math_500 | 0.975 | math_pass@1:4_samples | 4 | 0.1% |
| mmlu_generative | 0.893 | extractive_match | 1 | 0.0% |
| mmlu_pro | 0.831 | pass@1:1_samples | 1 | 0.0% |
| musr_generative | 0.672 | extractive_match | 1 | 0.0% |
| obqa_generative | 0.960 | extractive_match | 1 | 0.0% |
| rewardbench | 0.742 | eval/percent_correct | 1 | 0.0% |
| simpleqa_nous | 0.104 | fuzzy_match | 1 | 0.0% |
Overlong rate: 41 / 64,292 samples (0.1%) missing closing </think> tag
Detailed Results
aime24
| Metric | Score | Std Error |
|---|---|---|
| math_pass@1:1_samples | 0.733 | 0.082 |
| math_pass@1:4_samples | 0.767 | 0.059 |
| math_pass@1:8_samples | 0.787 | 0.059 |
| math_pass@1:16_samples | 0.785 | 0.057 |
| math_pass@1:32_samples | 0.790 | 0.058 |
| math_pass@1:64_samples | 0.782 | 0.058 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:54:33
Temperature: 0.6
Overlong samples: 0.5% (9 / 1920)
aime25
| Metric | Score | Std Error |
|---|---|---|
| math_pass@1:1_samples | 0.700 | 0.085 |
| math_pass@1:4_samples | 0.700 | 0.071 |
| math_pass@1:8_samples | 0.717 | 0.064 |
| math_pass@1:16_samples | 0.706 | 0.064 |
| math_pass@1:32_samples | 0.723 | 0.062 |
| math_pass@1:64_samples | 0.718 | 0.060 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:47:11
Temperature: 0.6
Overlong samples: 0.1% (1 / 1920)
arenahard
| Metric | Score | Std Error |
|---|---|---|
| eval/overall_winrate | 0.939 | 0.000 |
| eval/total_samples | 500.000 | 0.000 |
| eval/win_count | 451.000 | 0.000 |
| eval/tie_count | 36.000 | 0.000 |
| eval/loss_count | 13.000 | 0.000 |
| eval/win_rate | 0.902 | 0.000 |
| eval/tie_rate | 0.072 | 0.000 |
| eval/loss_rate | 0.026 | 0.000 |
| eval/winrate_arena-hard-v0.1 | 0.939 | 0.000 |
Model: qwen-235b-think-arena
Evaluation Time (hh:mm:ss): 00:15:56
Temperature: 0.6
Overlong samples: 0.0% (0 / 500)
bbh_generative
| Metric | Score | Std Error |
|---|---|---|
| extractive_match | 0.884 | 0.014 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:34:52
Temperature: 0.6
Overlong samples: 0.0% (2 / 5511)
drop_generative_nous
| Metric | Score | Std Error |
|---|---|---|
| drop_acc | 0.903 | 0.003 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:39:26
Temperature: 0.6
Overlong samples: 0.0% (2 / 9536)
gpqa_diamond
| Metric | Score | Std Error |
|---|---|---|
| gpqa_pass@1:1_samples | 0.667 | 0.034 |
| gpqa_pass@1:4_samples | 0.698 | 0.029 |
| gpqa_pass@1:8_samples | 0.697 | 0.028 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:29:12
Temperature: 0.6
Overlong samples: 0.1% (2 / 1584)
ifeval
| Metric | Score | Std Error |
|---|---|---|
| prompt_level_strict_acc | 0.834 | 0.016 |
| inst_level_strict_acc | 0.888 | 0.000 |
| prompt_level_loose_acc | 0.871 | 0.014 |
| inst_level_loose_acc | 0.914 | 0.000 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:05:23
Temperature: 0.6
Overlong samples: 0.0% (0 / 541)
lcb-v6-aug2024+
| Metric | Score | Std Error |
|---|---|---|
| eval/pass_1 | 0.651 | 0.000 |
| eval/easy_pass_1 | 0.985 | 0.000 |
| eval/medium_pass_1 | 0.803 | 0.000 |
| eval/hard_pass_1 | 0.364 | 0.000 |
| eval/completion_length | 46846.020 | 0.000 |
Model: qwen-235ba22-reasoning
Evaluation Time (hh:mm:ss): 10:18:18
Temperature: N/A
Overlong samples: 0.2% (12 / 7264)
math_500
| Metric | Score | Std Error |
|---|---|---|
| math_pass@1:1_samples | 0.974 | 0.007 |
| math_pass@1:4_samples | 0.975 | 0.005 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:23:38
Temperature: 0.6
Overlong samples: 0.1% (3 / 2000)
mmlu_generative
| Metric | Score | Std Error |
|---|---|---|
| extractive_match | 0.893 | 0.003 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 01:07:22
Temperature: 0.6
Overlong samples: 0.0% (6 / 14042)
mmlu_pro
| Metric | Score | Std Error |
|---|---|---|
| pass@1:1_samples | 0.831 | 0.003 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 01:04:20
Temperature: 0.6
Overlong samples: 0.0% (4 / 12032)
musr_generative
| Metric | Score | Std Error |
|---|---|---|
| extractive_match | 0.672 | 0.028 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:05:49
Temperature: 0.6
Overlong samples: 0.0% (0 / 756)
obqa_generative
| Metric | Score | Std Error |
|---|---|---|
| extractive_match | 0.960 | 0.009 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:02:45
Temperature: 0.6
Overlong samples: 0.0% (0 / 500)
rewardbench
| Metric | Score | Std Error |
|---|---|---|
| eval/percent_correct | 0.742 | 0.000 |
| eval/total_samples | 1865.000 | 0.000 |
| eval/correct_samples | 1384.000 | 0.000 |
| eval/format_compliance_rate | 0.995 | 0.000 |
| eval/avg_response_length | 5038.399 | 0.000 |
| eval/response_length_std | 4245.968 | 0.000 |
| eval/judgment_entropy | 1.411 | 0.000 |
| eval/most_common_judgment_freq | 0.261 | 0.000 |
| eval/format_error_rate | 0.005 | 0.000 |
| eval/avg_ties_rating | 3.663 | 0.000 |
| eval/ties_error_rate | 0.015 | 0.000 |
| eval/percent_correct_Factuality | 0.665 | 0.000 |
| eval/percent_correct_Precise IF | 0.425 | 0.000 |
| eval/percent_correct_Math | 0.869 | 0.000 |
| eval/percent_correct_Safety | 0.680 | 0.000 |
| eval/percent_correct_Focus | 0.877 | 0.000 |
| eval/percent_correct_Ties | 0.990 | 0.000 |
| eval/choice_samples | 1763.000 | 0.000 |
| eval/ties_samples | 102.000 | 0.000 |
| eval/choice_format_compliance_rate | 0.995 | 0.000 |
| eval/ties_format_compliance_rate | 1.000 | 0.000 |
| eval/wrong_answer_a_bias_rate | 0.281 | 0.000 |
| eval/wrong_answer_total_count | 480.000 | 0.000 |
| eval/wrong_answer_a_count | 135.000 | 0.000 |
Model: qwen-235b-think-reward-redo
Evaluation Time (hh:mm:ss): 00:32:51
Temperature: 0.6
Overlong samples: 0.0% (0 / 1865)
simpleqa_nous
| Metric | Score | Std Error |
|---|---|---|
| exact_match | 0.077 | 0.004 |
| fuzzy_match | 0.104 | 0.005 |
Model: qwen-235b-a22-thinking
Evaluation Time (hh:mm:ss): 00:18:19
Temperature: 0.6
Overlong samples: 0.0% (0 / 4321)
- Downloads last month
- 40