Edison Advances
Benchmarks / LABBench2

TableQA2

tableqa2

10 runs · 5 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 gpt-5-2-pro tools,high inject 0.700 4.3k 4.9m 2026-02-03
2 gemini-3-pro-preview tools,high inject 0.630 369 2.2m 2026-02-03
3 gpt-5-2 tools,high inject 0.630 4.3k 2.5m 2026-02-03
4 claude-opus-4-6 tools,high inject 0.590 2.3k 2.2m 2026-03-23
5 claude-opus-4-5 tools,high inject 0.450 880 47.1s 2026-03-22
6 gpt-5-2 — inject 0.100 55 2.0s 2026-02-03
7 claude-opus-4-6 — inject 0.090 219 7.2s 2026-03-20
8 gpt-5-2-pro — inject 0.090 1.0k 1.5m 2026-02-03
9 gemini-3-pro-preview — inject 0.080 224 1.5m 2026-02-03
10 claude-opus-4-5 — inject 0.040 229 7.4s 2026-03-20

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