Full technical report PDF: https://huggingface.co/spaces/tri-fair-lab/publications/blob...

> In this report, we argue that frontier performance can be achieved by a wide range of institutions through Continual Learning on readily available open-weight models.

> As opposed to existing limited approaches such as small-scale fine-tuning, prompt engineering, or tool-augmentation with a frozen model, our Continual Learning approach takes advantage of the effectiveness of a modern mid- & post-training stack while introducing safeguards preserving both plasticity and stability at each training stage and seeking to make the minimal number of high-impact interventions on the parameters.

Benchmark overall score comparisons:

> Large: Thomson 1.0-Large - 78.5, Opus 4.8 - 79.5, Gemini 3.1 Pro - 78.0, GPT 5.4 - 76.5, Qwen3.5 397B - 73.0, Snowdon 1.0-Large - 73.6

> Small: Thomson 1.0-Small - 74.6, Gemma4 31B - 71.2, Snowdon 1.1-Small - 71.7, Qwen3.6 35B - 71.7

For the large model, Thomson is utilizing the fine tuning stack they describe in the article, running it on Snowdon 1.0-Large, which in turn is a fine tune of Qwen3.5 397B. For the small model, it's a fine tune of Snowdon 1.1-Small, which is a fine tune of Qwen3.6 35B.

As for the small version's run:

> The full pipeline consumed approximately 1.63 × 10²³ FLOP over 35,207 B200 GPU-hours, showing that these results are achievable with compute and personnel budgets substantially lower than commonly thought.

That would amount to around quarter to half a million dollars of spend on that run.