SOOFI Accused of Inventing Metrics to Inflate Capabilities
JJitsev · x · 2026-07-19
The author dismisses SOOFI's "frontier-level / champion" claims as baseless. The project allegedly invented a "capability index" that no one else uses to score itself, subsequently claiming to be on par with or even superior to the original Nemotron-3-Nano.
He also points out the contradiction with the report's "transparency" narrative. Drawing conclusions based on custom metrics and larger training volumes—without transparently stating these premises—is highly misleading to readers.
Related event: European Open-Source Model SOOFI Accused of Eval Leakage and Overhype(11 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11