A user says the model regresses on knowledge versus its predecessor and on LCR.
A user previously floated a 45–46 ranking and 57% on Vals for V4.1-Flash-1017. They now call it DeepSeek's least hallucinatory model of 2026, but say it regresses on knowledge versus its predecessor and on LCR. They also say Sol Pareto-dominates it at peak price.
7.7K
3 Sources, first seen ago
> 45-46 would be decent (it's better than Grok, but will get tanked by Omniscience again). Surprise: V4.1-Flash-1017 is THE LEAST hallucinatory DeepSeek model in 2026 (though also regresses on knowledge vs its predecessor. And on LCR). But… Pareto-mogged by Sol.* *at peak…
yeah, speaking of. Any guesses as to where V4.1F-1017 will rank? not that AA is perfect by any means, eg they still use broken CritPt, but… I feel like 45-46 would be decent (it's better than Grok, but will get tanked by Omniscience again). 57% on Vals sounds fair, too.…
Not enough discussion yet.
No sentiment analysis available yet.
Not enough discussion yet.
No sentiment analysis available yet.
—
Not ranked yet
—
Not ranked yet
