Liquid LFM2.5 24B Card - τ³-Bench Banking: leaderboard
Liquid LFM2.5 24B Card - τ³-Bench Banking. Official LiquidAI post-trained checkpoint card;all models vLLM;officialGPT5.2lowuser,BM25retrieval,temperature0,16384tokens. Source table cohort fixed; no inference from similarly named base, FP8 or DSpark checkpoints. Metric: Score (%). Primary published table; source configurations remain distinct.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 35B A3B | 7.63 | #217 |
| 2 | Nemotron Lightning 3.5 30B A3B | 7.01 | #378 |
| 3 | Gemma 4 26B A4B (IT) | 4.54 | #288 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=liquid-lfm2-5-24b-card-bench-banking · How It Works · Data refreshed daily, snapshot 2026-10-16.