id stringlengths 5 34 | source stringclasses 7
values | domain stringclasses 22
values | kind stringclasses 4
values | gold stringlengths 1 4.15k | prompt stringlengths 16 6.51k | has_image bool 1
class | est_tokens int64 6 259k | prompt_truncated bool 2
classes | router_input stringlengths 35 6.53k | route stringclasses 150
values | agent_results stringlengths 588 666 | messages listlengths 3 3 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
mmlupro-530 | mmlu_pro | economics | mc | J | The sales tax that you pay at the grocery store is commonly labeled a
A. direct tax.
B. indirect tax.
C. flat tax.
D. luxury tax.
E. ad valorem tax.
F. inheritance tax.
G. progressive tax.
H. proportional tax.
I. excise tax.
J. regressive tax. | false | 82 | false | [input ~0k tokens]
The sales tax that you pay at the grocery store is commonly labeled a
A. direct tax.
B. indirect tax.
C. flat tax.
D. luxury tax.
E. ad valorem tax.
F. inheritance tax.
G. progressive tax.
H. proportional tax.
I. excise tax.
J. regressive tax. | {"domain": "economics", "difficulty": "hard", "strategy": "ensemble", "agents": ["glm-5.3-flash", "qwen3.8-27b", "nemotron-ultra"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 11, "latency": 0.0979154109954834, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 1308, "latency": 23.0334415435791, "skipped": null}, "nemotron-lightning": {"correct": false, "completion_tokens": 1926, "latency": 107.8952374458313, "skipped":... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-406 | gsm8k | math | num | 12 | Levi and his brother were playing basketball. Levi had scored 8 times and his brother had scored 12 times. Levi was determined to beat his brother by at least 5 baskets. How many more times does Levi have to score in order to reach his goal if his brother scores another 3 times? | false | 94 | false | [input ~0k tokens]
Levi and his brother were playing basketball. Levi had scored 8 times and his brother had scored 12 times. Levi was determined to beat his brother by at least 5 baskets. How many more times does Levi have to score in order to reach his goal if his brother scores another 3 times? | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 16, "latency": 0.1342310905456543, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 2189, "latency": 44.75338673591614, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 588, "latency": 32.65750312805176, "skipped": ... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
math-258 | math | math | math | \frac{20}{3} | Find the value of $x$ that satisfies $\frac{\sqrt{3x+5}}{\sqrt{6x+5}}=\frac{\sqrt{5}}{3}$. Express your answer as a common fraction. | false | 45 | false | [input ~0k tokens]
Find the value of $x$ that satisfies $\frac{\sqrt{3x+5}}{\sqrt{6x+5}}=\frac{\sqrt{5}}{3}$. Express your answer as a common fraction. | {"domain": "math", "difficulty": "medium", "strategy": "single", "agents": ["nemotron-lightning"]} | {"gemma-3-1b": {"correct": true, "completion_tokens": 157, "latency": 0.7152402400970459, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 1158, "latency": 20.53509211540222, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 716, "latency": 40.44672989845276, "skipped": n... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
longbench-66ed211f821e116aacb1ee0d | longbench | long:Single-Document QA | mc | C | Read the following text and answer the question.
Silence
Table Of Contents
Translator’s Preface
Prologue
Chapter 1
Chapter 2
Chapter 3
Chapter 4
Chapter 5
Chapter 6
Chapter 7
Chapter 8
Chapter 9
Chapter 10
Appendix
Translator’s Preface
SHUSAKU ENDO has been called the Japanese Graham Greene. If t... | false | 139,763 | true | [input ~139k tokens]
Read the following text and answer the question.
Silence
Table Of Contents
Translator’s Preface
Prologue
Chapter 1
Chapter 2
Chapter 3
Chapter 4
Chapter 5
Chapter 6
Chapter 7
Chapter 8
Chapter 9
Chapter 10
Appendix
Translator’s Preface
SHUSAKU ENDO has been called the Japanes... | {"domain": "long:Single-Document QA", "difficulty": "hard", "strategy": "single", "agents": ["nemotron-ultra"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "kimi-vl": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "nemotron-lightning": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "glm-5.3-flash": {"correct": fal... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
arc-34 | arc | science | mc | C | A snack consists of peanuts, sunflower seeds, raisins, almonds, and chocolate pieces. Which statement describes why this is a mixture?
A. It is made up of more than one substance.
B. It is impossible to separate the substances.
C. The components retain their original properties.
D. The components chemically combine wi... | false | 112 | false | [input ~0k tokens]
A snack consists of peanuts, sunflower seeds, raisins, almonds, and chocolate pieces. Which statement describes why this is a mixture?
A. It is made up of more than one substance.
B. It is impossible to separate the substances.
C. The components retain their original properties.
D. The components ch... | {"domain": "science", "difficulty": "easy", "strategy": "single", "agents": ["kimi-vl"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 18, "latency": 0.13715767860412598, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 675, "latency": 11.915341854095459, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 394, "latency": 22.38786745071411, "skipped": ... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
longbench-67009bd8bb02136c067caba9 | longbench | long:Multi-Document QA | mc | B | Read the following text and answer the question.
IMF Executive Board Concludes 2024 Article IV Consultation
with the People’s Republic of China
FOR IMMEDIATE RELEASE
Washington, DC – August 2, 2024: The Executive Board of the International Monetary Fund
(IMF) concluded the Article IV consultation1 with the People’... | false | 237,357 | true | [input ~237k tokens]
Read the following text and answer the question.
IMF Executive Board Concludes 2024 Article IV Consultation
with the People’s Republic of China
FOR IMMEDIATE RELEASE
Washington, DC – August 2, 2024: The Executive Board of the International Monetary Fund
(IMF) concluded the Article IV consultat... | {"domain": "long:Multi-Document QA", "difficulty": "hard", "strategy": "single", "agents": ["nemotron-ultra"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "kimi-vl": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "nemotron-lightning": {"correct": false, "completion_tokens": 0, "latency": 0, "skipped": "context"}, "glm-5.3-flash": {"correct": fal... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
arc-35 | arc | science | mc | D | Which of the following is an example of a chemical change?
A. clouds forming
B. sugar dissolving
C. water freezing
D. a candle burning | false | 46 | false | [input ~0k tokens]
Which of the following is an example of a chemical change?
A. clouds forming
B. sugar dissolving
C. water freezing
D. a candle burning | {"domain": "science", "difficulty": "easy", "strategy": "single", "agents": ["kimi-vl"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 10, "latency": 0.12470436096191406, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 420, "latency": 7.42043924331665, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 170, "latency": 9.535826921463013, "skipped": nu... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-914 | gsm8k | math | num | 250 | A plumber is trying to decide which of three different jobs he should take to make the most money. The first job involves fixing three toilets and three sinks at an apartment complex. The second involves two toilets and five sinks at a different apartment complex. The third involves fixing one toilet, two showers an... | false | 181 | false | [input ~0k tokens]
A plumber is trying to decide which of three different jobs he should take to make the most money. The first job involves fixing three toilets and three sinks at an apartment complex. The second involves two toilets and five sinks at a different apartment complex. The third involves fixing one toi... | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 167, "latency": 0.9671475887298584, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 544, "latency": 9.936633110046387, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 684, "latency": 38.51306509971619, "skipped": ... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
math-840 | math | math | math | 226 | How many integers between $100$ and $999$, inclusive, have the property that some permutation of its digits is a multiple of $11$ between $100$ and $999?$ For example, both $121$ and $211$ have this property.
$\mathrm{\textbf{(A)} \ }226\qquad \mathrm{\textbf{(B)} \ } 243 \qquad \mathrm{\textbf{(C)} \ } 270 \qquad \mat... | false | 127 | false | [input ~0k tokens]
How many integers between $100$ and $999$, inclusive, have the property that some permutation of its digits is a multiple of $11$ between $100$ and $999?$ For example, both $121$ and $211$ have this property.
$\mathrm{\textbf{(A)} \ }226\qquad \mathrm{\textbf{(B)} \ } 243 \qquad \mathrm{\textbf{(C)} ... | {"domain": "math", "difficulty": "hard", "strategy": "ensemble", "agents": ["glm-5.3-flash", "qwen3.8-27b", "nemotron-ultra"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 1292, "latency": 5.874611854553223, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 7809, "latency": 138.0980532169342, "skipped": null}, "nemotron-lightning": {"correct": false, "completion_tokens": 8192, "latency": 458.5001497268677, "skipped... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
math-166 | math | math | math | 16 | Josef and Timothy play a game in which Josef picks an integer between 1 and 1000 inclusive and Timothy divides 1000 by that integer and states whether or not the quotient is an integer. How many integers could Josef pick such that Timothy's quotient is an integer? | false | 89 | false | [input ~0k tokens]
Josef and Timothy play a game in which Josef picks an integer between 1 and 1000 inclusive and Timothy divides 1000 by that integer and states whether or not the quotient is an integer. How many integers could Josef pick such that Timothy's quotient is an integer? | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 9, "latency": 0.10058808326721191, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 1632, "latency": 28.894939422607422, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 532, "latency": 29.754047393798828, "skipped"... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mmlupro-115 | mmlu_pro | math | mc | B | In a set of 20 positive integers, at least how many pairs of numbers have a difference that is a multiple of 10?
A. 15
B. 10
C. 2
D. 30
E. 5
F. 9
G. 20
H. 25
I. 18
J. 35 | false | 57 | false | [input ~0k tokens]
In a set of 20 positive integers, at least how many pairs of numbers have a difference that is a multiple of 10?
A. 15
B. 10
C. 2
D. 30
E. 5
F. 9
G. 20
H. 25
I. 18
J. 35 | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 5, "latency": 0.08773946762084961, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 3332, "latency": 64.52770042419434, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 1700, "latency": 96.02236676216125, "skipped": ... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-849 | gsm8k | math | num | 56 | At a cafe, the breakfast plate has two eggs and twice as many bacon strips as eggs. If 14 customers order breakfast plates, how many bacon strips does the cook need to fry? | false | 58 | false | [input ~0k tokens]
At a cafe, the breakfast plate has two eggs and twice as many bacon strips as eggs. If 14 customers order breakfast plates, how many bacon strips does the cook need to fry? | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": true, "completion_tokens": 117, "latency": 0.5473625659942627, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 371, "latency": 6.741529941558838, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 301, "latency": 16.598836183547974, "skipped": ... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-513 | gsm8k | math | num | 5400 | Sheila, Purity, and Rose want to rent a house. Sheila has offered to pay five times Purity’s share of the rent. Rose can only afford thrice what Purity pays. If Rose’s share is $1,800, what is the total house rent? | false | 72 | false | [input ~0k tokens]
Sheila, Purity, and Rose want to rent a house. Sheila has offered to pay five times Purity’s share of the rent. Rose can only afford thrice what Purity pays. If Rose’s share is $1,800, what is the total house rent? | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["kimi-vl"]} | {"gemma-3-1b": {"correct": true, "completion_tokens": 219, "latency": 1.0727994441986084, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 566, "latency": 11.022974729537964, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 400, "latency": 22.55622386932373, "skipped": n... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mbpp-308 | mbpp | code | code |
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],3)==[60, 54, 50]
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],4)==[60, 54, 50, 48]
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],5)==[60, 54, 50, 48, 45] | Write a function to find the specified number of largest products from two given lists.
Your code should pass these tests:
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],3)==[60, 54, 50]
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],4)==[60, 54, 50, 48]
assert large_product([1, 2, 3, 4, 5, 6]... | false | 122 | false | [input ~0k tokens]
Write a function to find the specified number of largest products from two given lists.
Your code should pass these tests:
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],3)==[60, 54, 50]
assert large_product([1, 2, 3, 4, 5, 6],[3, 6, 8, 9, 10, 6],4)==[60, 54, 50, 48]
assert large_product... | {"domain": "code", "difficulty": "easy", "strategy": "single", "agents": ["nemotron-lightning"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 157, "latency": 0.7530515193939209, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 1661, "latency": 29.149763345718384, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 1433, "latency": 94.16099333763123, "skipped"... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mmlupro-358 | mmlu_pro | law | mc | I | Ann, Bea, and Carla were three friends who lived in the same neighborhood. While Ann was away on a business trip, someone broke into her garage and stole her golf clubs. The next week, Ann was planning to go on vacation and asked Bea if she could borrow her golf clubs. Bea agreed and loaned her golf clubs to Ann, who p... | false | 1,102 | false | [input ~1k tokens]
Ann, Bea, and Carla were three friends who lived in the same neighborhood. While Ann was away on a business trip, someone broke into her garage and stole her golf clubs. The next week, Ann was planning to go on vacation and asked Bea if she could borrow her golf clubs. Bea agreed and loaned her golf ... | {"domain": "law", "difficulty": "medium", "strategy": "single", "agents": ["nemotron-ultra"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 42, "latency": 0.2638862133026123, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 4533, "latency": 80.58361959457397, "skipped": null}, "nemotron-lightning": {"correct": false, "completion_tokens": 8192, "latency": 456.5448021888733, "skipped"... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-926 | gsm8k | math | num | 12834 | A hay farmer harvested 560 bales of hay from 5 acres of grass per month last year. This year, he planted an additional 7 acres of grass. If the farmer also owns 9 horses and each horse consumes 3 bales of hay a day, how many bales of hay would the farmer have left by the end of December if he starts feeding them this y... | false | 123 | false | [input ~0k tokens]
A hay farmer harvested 560 bales of hay from 5 acres of grass per month last year. This year, he planted an additional 7 acres of grass. If the farmer also owns 9 horses and each horse consumes 3 bales of hay a day, how many bales of hay would the farmer have left by the end of December if he starts ... | {"domain": "math", "difficulty": "hard", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 1695, "latency": 8.200483798980713, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 1288, "latency": 23.032359838485718, "skipped": null}, "nemotron-lightning": {"correct": false, "completion_tokens": 8192, "latency": 458.3634524345398, "skippe... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mbpp-904 | mbpp | code | code |
assert even_num(13.5)==False
assert even_num(0)==True
assert even_num(-9)==False | Write a function to return true if the given number is even else return false.
Your code should pass these tests:
assert even_num(13.5)==False
assert even_num(0)==True
assert even_num(-9)==False | false | 65 | false | [input ~0k tokens]
Write a function to return true if the given number is even else return false.
Your code should pass these tests:
assert even_num(13.5)==False
assert even_num(0)==True
assert even_num(-9)==False | {"domain": "code", "difficulty": "easy", "strategy": "single", "agents": ["nemotron-lightning"]} | {"gemma-3-1b": {"correct": true, "completion_tokens": 94, "latency": 0.464155912399292, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 2411, "latency": 42.3182635307312, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 867, "latency": 52.10533785820007, "skipped": null... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mbpp-580 | mbpp | code | code |
assert extract_even((4, 5, (7, 6, (2, 4)), 6, 8)) == (4, (6, (2, 4)), 6, 8)
assert extract_even((5, 6, (8, 7, (4, 8)), 7, 9)) == (6, (8, (4, 8)))
assert extract_even((5, 6, (9, 8, (4, 6)), 8, 10)) == (6, (8, (4, 6)), 8, 10) | Write a function to extract the even elements in the nested mixed tuple.
Your code should pass these tests:
assert extract_even((4, 5, (7, 6, (2, 4)), 6, 8)) == (4, (6, (2, 4)), 6, 8)
assert extract_even((5, 6, (8, 7, (4, 8)), 7, 9)) == (6, (8, (4, 8)))
assert extract_even((5, 6, (9, 8, (4, 6)), 8, 10)) == (6, (8, (4, ... | false | 111 | false | [input ~0k tokens]
Write a function to extract the even elements in the nested mixed tuple.
Your code should pass these tests:
assert extract_even((4, 5, (7, 6, (2, 4)), 6, 8)) == (4, (6, (2, 4)), 6, 8)
assert extract_even((5, 6, (8, 7, (4, 8)), 7, 9)) == (6, (8, (4, 8)))
assert extract_even((5, 6, (9, 8, (4, 6)), 8, 1... | {"domain": "code", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 169, "latency": 1.1395599842071533, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 1610, "latency": 27.15511131286621, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 2266, "latency": 201.41896629333496, "skipped... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
gsm8k-722 | gsm8k | math | num | 900 | Robi and Rudy contributed money to start a business that could earn them profit. Robi contributed $4000, and Rudy contributed 1/4 more money than Robi. If they made a profit of 20 percent of the total amount and decided to share the profits equally, calculate the amount of money each got. | false | 97 | false | [input ~0k tokens]
Robi and Rudy contributed money to start a business that could earn them profit. Robi contributed $4000, and Rudy contributed 1/4 more money than Robi. If they made a profit of 20 percent of the total amount and decided to share the profits equally, calculate the amount of money each got. | {"domain": "math", "difficulty": "easy", "strategy": "single", "agents": ["kimi-vl"]} | {"gemma-3-1b": {"correct": true, "completion_tokens": 183, "latency": 0.8668744564056396, "skipped": null}, "kimi-vl": {"correct": true, "completion_tokens": 646, "latency": 12.513733148574829, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 426, "latency": 23.92651915550232, "skipped": n... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
mmlupro-188 | mmlu_pro | history | mc | J | This question refers to the following information.
"The question, therefore, should be quickly settled, whether free colored persons, born and naturalized in this country, are not American citizens, and justly entitled to all the rights, privileges and immunities of citizens of the several states; and whether the Const... | false | 527 | false | [input ~0k tokens]
This question refers to the following information.
"The question, therefore, should be quickly settled, whether free colored persons, born and naturalized in this country, are not American citizens, and justly entitled to all the rights, privileges and immunities of citizens of the several states; an... | {"domain": "history", "difficulty": "easy", "strategy": "single", "agents": ["glm-5.3-flash"]} | {"gemma-3-1b": {"correct": false, "completion_tokens": 6, "latency": 0.08952951431274414, "skipped": null}, "kimi-vl": {"correct": false, "completion_tokens": 1935, "latency": 36.40868043899536, "skipped": null}, "nemotron-lightning": {"correct": true, "completion_tokens": 670, "latency": 38.088446378707886, "skipped":... | [
{
"role": "system",
"content": "You are Shaktimaan, an orchestrator. You do not answer the task yourself. You read the task and decide which agent(s) from the pool should handle it, minimising cost while maximising the chance of a correct answer.\nAgents (cheapest first): gemma-3-1b, kimi-vl, nemotron-light... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.