Domain Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75Accuracy
23
Mar 24, 2026
73Accuracy
23
Mar 24, 2026
60Accuracy
23
Mar 24, 2026
42.9Score
14
Jun 2, 2026
20.4Accuracy
4
Jul 7, 2026
19.5Accuracy
4
Jul 7, 2026
63Accuracy (MMLU Chemistry Domain Reasoning)
4
Jul 7, 2026
50.6Accuracy
4
Jul 7, 2026
25.6MMLU-Pro CS Domain Reasoning Accuracy
4
Jul 7, 2026
70.1MMLU CS Domain Reasoning Accuracy
4
Jul 7, 2026
70Accuracy (GPQA Bio)
4
Jul 7, 2026
53.2Accuracy (MMLU-Pro Biomedical)
4
Jul 7, 2026
70.2Accuracy
4
Jul 7, 2026
54.1Accuracy
4
Jul 7, 2026