Skip to main content

DeepSeek V3

Change Analysis · 2026-03-24-Same-Day Compare

DeepSeek V3 2026-03-24-Same-Day CompareGrounding (v5) dimension rose 2.1 pts

Score Comparison

75.1 75.7 +0.6
Dimension Previous Current Change
Code Execution (v5) 92.2 92.5 +0.3
Knowledge Synthesis (v5) 47.6 49 +1.4
Grounding (v5) 78.8 80.9 +2.1
Value 99.7 99.7 0
Stability 33.6 31.9 -1.7
Availability 100 100 0

All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.

Back to Movers