eval-result:mmlu.qwen-2-5-72b.001
eval-result:mmlu.qwen-2-5-72b.001
EvalResultbenchmarks/eval-results/eval-results-alibaba-qwen.yaml·Open in Graph → {
"id": "eval-result:mmlu.qwen-2-5-72b.001",
"_kind": "EvalResult",
"_file": "benchmarks/eval-results/eval-results-alibaba-qwen.yaml",
"_cluster": "benchmarks",
"attributes": {
"evalRunId": "eval-run:mmlu.qwen-2-5-72b.2024-09",
"metricName": "accuracy",
"score": 0.861,
"unit": "fraction",
"passFail": "pass",
"reportedAt": "2024-09-19T00:00:00Z"
},
"outgoingEdges": [
{
"from": "eval-result:mmlu.qwen-2-5-72b.001",
"to": "eval-run:mmlu.qwen-2-5-72b.2024-09",
"kind": "belongs_to_eval_run"
},
{
"from": "eval-result:mmlu.qwen-2-5-72b.001",
"to": "benchmark:mmlu",
"kind": "scored_against",
"attributes": {}
}
],
"incomingEdges": [
{
"from": "eval-run:gaia.claude-code.2025",
"to": "eval-result:mmlu.qwen-2-5-72b.001",
"kind": "produced_result",
"attributes": {}
}
]
}