PatentAgentBench - Codex - Design FTO: leaderboard
PatentAgentBench Design FTO evaluates patent evidence search, comparison, drafting, responses and translation under Codex CLI 0.151.0. Its primary Macro Recall@200 (%) uses the full assigned case denominator, including final failures after up to three execution-failure retries. Harnesses and unreported model effort remain distinct source configurations. The suite has 510 patent cases; its public banks contain 1,311 records because translation's 80 cases contain 881 segment items.
Metric: Macro Recall@200 (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (PatentAgentBench Run: 2610.35031v1; GPT-5.6-Sol; Codex CLI 0.151.0; effort unreported) | 0.4 | |
| 2 | Qwen 3.8 Max (PatentAgentBench Run: 2610.35031v1; Qwen3.8-Max; Codex CLI 0.151.0; effort unreported) | 0 | |
| 3 | Kimi K3 (PatentAgentBench Run: 2610.35031v1; Kimi K3; Codex CLI 0.151.0; effort unreported) | 0 | |
| 4 | DeepSeek V4 Pro (PatentAgentBench Run: 2610.35031v1; DeepSeek-V4-Pro; Codex CLI 0.151.0; effort unreported) | 0 | |
| 5 | MiniMax-M3 (PatentAgentBench Run: 2610.35031v1; MiniMax-M3; Codex CLI 0.151.0; effort unreported) | 0 | |
| 6 | GLM-5.3 (PatentAgentBench Run: 2610.35031v1; GLM-5.3; Codex CLI 0.151.0; effort unreported) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=patentagentbench-codex-design-fto · How It Works · Data refreshed daily, snapshot 2026-11-05.