============================================================
RACE EVAL AGGREGATE STATS (10 runs)
============================================================

Comprehensiveness:
  Mean:     0.5499
  Std Dev:  0.000957
  Variance: 0.00000092
  Min:      0.5479
  Max:      0.5511

Insight:
  Mean:     0.5683
  Std Dev:  0.001492
  Variance: 0.00000222
  Min:      0.5658
  Max:      0.5710

Instruction Following:
  Mean:     0.5298
  Std Dev:  0.001087
  Variance: 0.00000118
  Min:      0.5283
  Max:      0.5315

Readability:
  Mean:     0.5239
  Std Dev:  0.001625
  Variance: 0.00000264
  Min:      0.5213
  Max:      0.5261

Overall Score:
  Mean:     0.5481
  Std Dev:  0.000764
  Variance: 0.00000058
  Min:      0.5468
  Max:      0.5492

------------------------------------------------------------
Per-run scores (included for reference)
------------------------------------------------------------
Comprehensiveness: 0.5507, 0.5496, 0.5496, 0.5489, 0.5506, 0.5503, 0.5504, 0.5479, 0.5511, 0.5502
Insight: 0.5710, 0.5668, 0.5682, 0.5680, 0.5684, 0.5658, 0.5689, 0.5688, 0.5700, 0.5675
Instruction Following: 0.5299, 0.5299, 0.5315, 0.5284, 0.5309, 0.5307, 0.5290, 0.5283, 0.5291, 0.5304
Readability: 0.5241, 0.5228, 0.5249, 0.5261, 0.5252, 0.5218, 0.5255, 0.5213, 0.5244, 0.5229
Overall Score: 0.5492, 0.5474, 0.5483, 0.5478, 0.5489, 0.5474, 0.5486, 0.5468, 0.5487, 0.5481
