Edison Advances
Benchmarks / LABBench2

TableQA2 (pdf)

tableqa2-pdf

10 runs · 5 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 claude-opus-4-6 tools,high file 0.880 784 46.3s 2026-03-23
2 gemini-3-pro-preview — file 0.880 88 41.8s 2026-02-03
3 gemini-3-pro-preview tools,high file 0.880 202 53.3s 2026-02-03
4 claude-opus-4-5 tools,high file 0.850 837 29.6s 2026-03-22
5 gpt-5-2 tools,high file 0.840 1.3k 4.1m 2026-02-03
6 gpt-5-2-pro — file 0.820 464 2.4m 2026-02-03
7 claude-opus-4-6 — file 0.810 138 38.2s 2026-03-20
8 gpt-5-2-pro tools,high file 0.800 838 4.0m 2026-02-03
9 gpt-5-2 — file 0.760 72 1.9m 2026-02-03
10 claude-opus-4-5 — file 0.750 222 21.9s 2026-03-20

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