Edison Advances
Benchmarks / LABBench2

FigQA2 (image)

figqa2-img

10 runs · 5 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 gpt-5-2 tools,high file 0.663 4.6k 8.1m 2026-02-03
2 gpt-5-2-pro — file 0.614 570 1.8m 2026-02-03
3 gemini-3-pro-preview — file 0.604 277 1.8m 2026-02-03
4 gpt-5-2-pro tools,high file 0.594 1.4k 2.8m 2026-02-03
5 gpt-5-2 — file 0.564 78 12.2s 2026-02-03
6 gemini-3-pro-preview tools,high file 0.545 5.4k 3.9m 2026-02-03
7 claude-opus-4-5 tools,high file 0.446 1.1k 21.6s 2026-03-22
8 claude-opus-4-5 — file 0.426 183 8.0s 2026-03-20
9 claude-opus-4-6 — file 0.416 165 8.6s 2026-03-20
10 claude-opus-4-6 tools,high file 0.406 1.7k 41.0s 2026-03-22

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