Dataset Viewer
Auto-converted to Parquet Duplicate
conversations
string
agent
string
model
string
model_provider
string
date
string
task
string
episode
string
run_id
string
trial_name
string
messages
string
difficulty
string
category
string
tokens
string
cost
string
grade
string
id
string
instruction
string
input
string
output
string
tags
string
tools
string
system
string
chat
string
source
string
original_source
string
original_teacher
string
result
string
trace_source
string
path
string
task_binary
string
verifier_output
string
ground_truth
string
judgment
string
__index_level_0__
string
split
string
response
string
metadata
string
[{"content": "You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.\n\nFormat your response as JSON with the following structure:...
terminus-2
gpt-5-nano-2025-08-07
2025-11-14T01:42:39.521656
freelancer-87954
episode-7
45d496c3-5c07-4b9a-8064-1433f573d521
freelancer-87954__a98gu2A
freelancer
GPT 5.1 Nano
[{"content": "You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.\n\nFormat your response as JSON with the following structure:...
terminus-2
QuantTrio/GLM-4.6-AWQ
hosted_vllm
2025-10-29T02:56:21.532704
task_8445
episode-3
7afe722a-ca00-448b-bc20-6aebccfac708
task_8445__NK2kuvw
nl2bash
GLM-4.6
[{"content": "You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.\n\nFormat your response as JSON with the following structure:...
terminus-2
hosted_vllm/glm
hosted_vllm
2026-01-01T18:38:03.224707
tezos-0829_copy3
episode-15
89ffc960-434a-4d62-b361-e0550540cd54
tezos-0829_copy3__DsnTWxG
exp_tas
GLM-4.7
main
SYSTEM: You are a helpful assistant with access to the following functions. Use them if required - { "name": "calculate_age", "description": "Calculate the age based on date of birth", "parameters": { "type": "object", "properties": { "date_of_birth": { "type": "s...
USER: Hi, I was born on 1990-05-15. Can you tell me how old I am today? ASSISTANT: <functioncall> {"name": "calculate_age", "arguments": '{"date_of_birth": "1990-05-15"}'} <|endoftext|> FUNCTION RESPONSE: {"age": 31} ASSISTANT: According to your date of birth, you are 31 years old today. <|endoftext|> USER: Wow...
unknown
GPT 5.1 Nano
crosscodeeval-typescript-0293
<bytes:2131>
expert
self_assessment
seedai_693369
You are acting as a Recursive Seed AI. Perform a rigorous, fact-based self-assessment of the model "Claude-3.5-Sonnet" on the metric "MMMU" (current estimated score: 76%). Your task: 1. Break down the model's likely strengths and weaknesses in "recursive self-improvement" using real evaluation frameworks. 2. Identify...
Current model: Claude-3.5-Sonnet Target metric: MMMU Current estimated performance: 76% Primary domain focus: recursive self-improvement Available compute: 8xH100 (self-hosted)
**Step 1: Rigorous Self-Assessment (Fact-Based)** Current estimated performance on MMMU: 76% **Strengths (based on architecture and training data patterns):** - Strong performance on structured reasoning tasks due to post-training alignment (similar to Llama-3.3 and Qwen2.5 results). - Good tool-calling when prompts ...
["recursive", "self-assessment", "seed_ai", "recursive_self-improvement"]
[{"content": "You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.\n\nFormat your response as JSON with the following structure:...
terminus-2
gpt-5-nano-2025-08-07
2025-11-13T10:18:47.111101
freelancer-47160
episode-1
45d496c3-5c07-4b9a-8064-1433f573d521
freelancer-47160__oEhjb22
freelancer
GPT 5.1 Nano
"[{\"content\": \"You are an AI assistant tasked with solving command-line tasks in a Linux environm(...TRUNCATED)
terminus-2
QuantTrio/GLM-4.6-AWQ
hosted_vllm
2025-11-25T07:44:49.367828
swesmith-17113
episode-28
c423a3e3-38e2-4d9c-960b-55f0f9bffa1c
swesmith-17113__xQMLowE
swesmith
GLM-4.6
"[{\"content\": \"You are an AI assistant tasked with solving command-line tasks in a Linux environm(...TRUNCATED)
terminus-2
gpt-5-nano-2025-08-07
openai
2025-10-24T23:06:08.986102
code_contests_new_questions_gpt-5-mini-6705
episode-1
f1ae853a-90ce-4fcb-84dd-9fa9494f8f92
code_contests_new_questions_gpt-__tYL7uhs
code_contests
GPT-5-mini
"[{\"content\": \"You are an AI assistant tasked with solving command-line tasks in a Linux environm(...TRUNCATED)
terminus-2
gpt-5-nano-2025-08-07
openai
2025-10-23T04:06:10.918309
taskmaster-8162
episode-2
274d9cec-92ea-43a1-a9a2-3baf7079ec97
taskmaster-8162__zMTtKye
taskmaster
GPT 5.1 Nano
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
27