TIGA Taxonomy DBLP - Edge F1 - Harness TIGA 5-shot: leaderboard
TIGA Taxonomy DBLP - Edge F1 - Harness TIGA 5-shot: Taxonomy F1 (%). TIGA arXiv 2611.13966v1 Table 8: author-run ancestor and edge F1 on four taxonomy-induction datasets under HF, CoL and tool-grounded TIGA. GPT-5.4-mini and Gemma-4-31b, zero/five-shot settings retained. Raw F1 percentages are used, not normalized radar coordinates or cost/time. Decoding/effort unreported; no training of the backbone. Native source condition: Harness TIGA 5-shot.
Metric: Taxonomy F1 (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4-mini (Benchmark Sweep Run: source=tiga_paper; harness=TIGA; shot=5-shot; effort=unreported) | 57.6 | |
| 2 | Gemma-4-31b (Benchmark Sweep Run: source=tiga_paper; harness=TIGA; shot=5-shot; effort=unreported) | 55.3 |
Interactive version: theaggregate.ai/benchmark?slug=tiga-taxonomy-dblp-edge-f1-harness-tiga-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-12.