Edison Advances
Benchmarks / LABBench2

FigQA2

figqa2

10 runs · 5 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 gpt-5-2 tools,high inject 0.426 7.0k 4.0m 2026-02-03
2 gpt-5-2-pro tools,high inject 0.347 6.2k 8.0m 2026-02-03
3 claude-opus-4-6 tools,high inject 0.287 4.9k 4.0m 2026-03-22
4 claude-opus-4-5 tools,high inject 0.257 1.1k 1.4m 2026-03-22
5 gemini-3-pro-preview tools,high inject 0.238 443 3.4m 2026-02-03
6 gpt-5-2-pro — inject 0.119 1.1k 1.6m 2026-02-03
7 gpt-5-2 — inject 0.119 61 2.7s 2026-02-03
8 claude-opus-4-6 — inject 0.109 304 9.0s 2026-03-20
9 gemini-3-pro-preview — inject 0.109 264 2.0m 2026-02-03
10 claude-opus-4-5 — inject 0.079 259 7.1s 2026-03-20

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