DeepSeek V4.1 Flash / Together AI · Vals Inference Provider Index · Provider-specific task accuracy ↗
DeepSeek / MODEL EVIDENCE
DeepSeek V4.1 Flash / Together AI
1 benchmarks · 1 observations · 1 sources
Scores at a glance
1 benchmarks · large dot: DeepSeek V4.1 Flash / Together AI; small dots: closest models where reported
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
1 of 1 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
POST-TRAINING / SOURCE DISCLOSURE
What the DeepSeek V4.1 Flash / Flash 1017 report says
The Flash technical report describes a supervised starting stage, reinforcement learning across task domains, then distillation from an ensemble of teachers. It emphasizes synthesized tasks and scalable interactive environments.
- Supervised fine-tuning
- Multi-domain reinforcement learning
- Full-vocabulary on-policy distillation
- Concatenated routing replay for asynchronous rollouts
The report documents Flash. The 1017 card calls that release a minor update but does not supply a separate complete recipe; these stages should not be assumed to describe every DeepSeek V4.1 variant.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
Names used in source tables
DeepSeek V4.1 Flash / Together AI