Edison Advances
Benchmarks / LABBench2

DBQA2

dbqa2

10 runs · 5 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 gemini-3-pro-preview tools,high inject 0.453 567 3.1m 2026-01-26
2 gpt-5-2 tools,high inject 0.302 11.0k 6.4m 2026-01-25
3 claude-opus-4-6 tools,high inject 0.279 2.7k 3.6m 2026-03-22
4 claude-opus-4-5 tools,high inject 0.198 1.1k 1.4m 2026-03-22
5 gpt-5-2-pro tools,high inject 0.105 10.0k 14.6m 2026-01-25
6 claude-opus-4-6 — inject 0.093 257 7.9s 2026-03-20
7 gemini-3-pro-preview — inject 0.070 273 47.9s 2026-01-22
8 gpt-5-2-pro — inject 0.070 968 1.3m 2026-01-22
9 gpt-5-2 — inject 0.070 196 5.7s 2026-01-22
10 claude-opus-4-5 — inject 0.058 259 6.7s 2026-03-20

Click column headers to sort. Click mode chips to filter.