Shaktimaan / eval_results.json
podstack's picture
Shaktimaan v1.0
c1f5d12 verified
Raw History Blame Contribute Delete
2.9 kB
{
"n_test": 554,
"valid_json": 1.0,
"route_match": 0.5306859205776173,
"live_ensembles": 31,
"route_counts": {
"nemotron-lightning": 218,
"glm-5.3-flash": 192,
"kimi-vl": 80,
"glm-5.3-flash,qwen3.8-27b,nemotron-ultra": 32,
"nemotron-ultra": 31,
"qwen3.8-27b": 1
},
"policies": {
"shaktimaan": {
"accuracy": 0.8339,
"relative_cost": 0.424
},
"oracle": {
"accuracy": 0.8971,
"relative_cost": 0.49
},
"always:gemma-3-1b": {
"accuracy": 0.2563,
"relative_cost": 0.0024
},
"always:kimi-vl": {
"accuracy": 0.6137,
"relative_cost": 0.0736
},
"always:nemotron-lightning": {
"accuracy": 0.7563,
"relative_cost": 0.1089
},
"always:glm-5.3-flash": {
"accuracy": 0.7924,
"relative_cost": 0.0944
},
"always:qwen3.8-27b": {
"accuracy": 0.7888,
"relative_cost": 0.3641
},
"always:nemotron-ultra": {
"accuracy": 0.7852,
"relative_cost": 1.0
},
"rule:glm-5.3-flash": {
"accuracy": 0.8574,
"relative_cost": 0.1331
},
"rule:qwen3.8-27b": {
"accuracy": 0.8538,
"relative_cost": 0.4028
},
"rule:nemotron-ultra": {
"accuracy": 0.8267,
"relative_cost": 1.0009
}
},
"accuracy_by_source": {
"arc": {
"n": 75,
"shaktimaan": 0.987,
"oracle": 1.0,
"always:nemotron-ultra": 0.987,
"rule:glm-5.3-flash": 0.987,
"rule:qwen3.8-27b": 0.987
},
"chartqa": {
"n": 31,
"shaktimaan": 0.742,
"oracle": 0.742,
"always:nemotron-ultra": 0.0,
"rule:glm-5.3-flash": 0.742,
"rule:qwen3.8-27b": 0.742
},
"gsm8k": {
"n": 105,
"shaktimaan": 0.895,
"oracle": 0.981,
"always:nemotron-ultra": 0.971,
"rule:glm-5.3-flash": 0.962,
"rule:qwen3.8-27b": 0.981
},
"humaneval": {
"n": 18,
"shaktimaan": 0.889,
"oracle": 1.0,
"always:nemotron-ultra": 0.944,
"rule:glm-5.3-flash": 0.944,
"rule:qwen3.8-27b": 0.944
},
"longbench": {
"n": 32,
"shaktimaan": 0.594,
"oracle": 0.594,
"always:nemotron-ultra": 0.594,
"rule:glm-5.3-flash": 0.469,
"rule:qwen3.8-27b": 0.5
},
"math": {
"n": 106,
"shaktimaan": 0.755,
"oracle": 0.821,
"always:nemotron-ultra": 0.651,
"rule:glm-5.3-flash": 0.745,
"rule:qwen3.8-27b": 0.755
},
"mbpp": {
"n": 67,
"shaktimaan": 0.94,
"oracle": 1.0,
"always:nemotron-ultra": 0.97,
"rule:glm-5.3-flash": 0.985,
"rule:qwen3.8-27b": 0.925
},
"mmlu_pro": {
"n": 120,
"shaktimaan": 0.775,
"oracle": 0.875,
"always:nemotron-ultra": 0.742,
"rule:glm-5.3-flash": 0.833,
"rule:qwen3.8-27b": 0.817
}
},
"live_ensembles_solved": 11
}