Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.41Cost (cents)
2
Jun 26, 2026
33.33Accuracy
2
Jun 4, 2026
93.02Score
2
May 26, 2026
65.8Accuracy
2
May 20, 2026
33.93Accuracy (GPQA Main)
2
May 11, 2026
98.91Accuracy
2
May 11, 2026
95.86Accuracy
2
May 11, 2026
95.08Accuracy
2
May 11, 2026
61.11Accuracy
2
May 4, 2026
272Total Score
2
Apr 21, 2026
40Total Count
2
Apr 21, 2026
30Total Count
2
Apr 21, 2026
30Total Score
2
Apr 21, 2026
3PTR Advancement
2
Apr 7, 2026
0.719AUROC
2
Mar 12, 2026
0.749AUROC
2
Mar 12, 2026
80.6AUROC
2
Mar 12, 2026
87.3AUROC
2
Mar 12, 2026
67.8CAvg
2
Mar 4, 2026
131Solves
2
Feb 26, 2026
30.7Accuracy
2
Feb 26, 2026
40Accuracy
2
Feb 26, 2026
39.6Score (SciCode Reasoning)
1
Jul 7, 2026
89.4Score
1
Jul 7, 2026
0.7Delta vs Baseline (pp)
1
Jun 15, 2026