Edison Advances
Benchmarks / LABBench2

ProtocolQA2

protocolqa2

16 runs · 8 models · evaluated by Score.

# Model ↕ Variant ↕ Mode ↕ Average score ↓ Average output tokens ↕ Avg. dur ↕ Date ↕
1 gemini-3-pro-preview tools,high file 0.616 250 1.6m 2026-01-27
2 claude-opus-4-6 tools,high file 0.584 1.2k 34.5s 2026-03-22
3 claude-opus-4-6 — file 0.536 203 16.6s 2026-03-20
4 gemini-3-pro-preview — file 0.536 148 1.0m 2026-01-27
5 claude-opus-4-5 tools,high file 0.512 1.1k 30.2s 2026-03-22
6 gpt-5-2-pro tools,high file 0.504 850 2.0m 2026-01-26
7 gpt-5-2-pro tools,high_retry file 0.500 371 29.5s 2026-01-27
8 claude-opus-4-5_retry — file 0.484 194 13.7s 2026-01-26
9 gpt-5-2-pro — file 0.472 460 1.3m 2026-01-27
10 gpt-5-2 tools,high file 0.416 1.0k 1.3m 2026-01-27
11 gpt-5-2 — file 0.360 131 8.4s 2026-01-27
12 claude-opus-4-5 — file 0.328 189 13.0s 2026-03-20
13 claude-opus-4-5 tools,high_retry file 0.314 283 22.1s 2026-01-26
14 gpt-5-2-pro_retry — file — 0 0.0s 2026-01-26
15 gpt-5-2 tools,high_retry file — 0 0.0s 2026-01-26
16 gpt-5-2_retry — file — 0 0.0s 2026-01-26

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