TIGA Taxonomy DBLP - Ancestor F1 - Harness CoL 5-shot: leaderboard
TIGA Taxonomy DBLP - Ancestor F1 - Harness CoL 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 CoL 5-shot.
Metric: Taxonomy F1 (%). Source: arxiv.org. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B | 77.99 | #393 |
| 2 | GPT-5.4 Mini | 52.9 | #389 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=tiga-taxonomy-dblp-ancestor-f1-harness-col-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-12.