feature: add classification evaluators (#1397) #4162

Job	Run time
discover-testcases	5s
basic-testcase / alpha	30s
apicalls-testcase / cloud	39s
basic-testcase / cloud	36s
calculator-evals / cloud	2m 59s
eval-level-expected-output / cloud	43s
basic-testcase / staging	39s
eval-input-overrides / cloud	35s
apicalls-testcase / alpha	41s
eval-input-overrides / staging	29s
eval-spans-testcase / cloud	1m 11s
calculator-crash-evals / staging	33s
calculator-evals / alpha	3m 26s
calculator-evals / staging	3m 18s
csv-processor-evals / cloud	36s
csv-processor-evals / staging	37s
apicalls-testcase / staging	41s
eval-level-expected-output / staging	38s
csv-processor-evals / alpha	34s
calculator-crash-evals / alpha	36s
calculator-crash-evals / cloud	32s
eval-telemetry-testcase / staging	1m 46s
target-output-key-evals / staging	32s
tools-evals / alpha	46s
eval-spans-testcase / alpha	1m 28s
eval-spans-testcase / staging	1m 15s
eval-telemetry-testcase / cloud	1m 33s
eval-level-expected-output / alpha	40s
langchain-cross / staging	34s
tools-evals / staging	40s
target-output-key-evals / cloud	35s
eval-input-overrides / alpha	33s
langchain-cross / cloud	36s
target-output-key-evals / alpha	30s
tools-evals / cloud	38s
langchain-cross / alpha	38s
eval-telemetry-testcase / alpha	1m 42s
summarize-results	3s
	35m 7s

Provide feedback