Skip to main content

Benchmark profile

FACTS Parametric

A parametric factuality benchmark reported in DeepSeek-V4 base-model evaluations.

Data verified

Benchmark score on FACTS Parametric — July 23, 2026

BenchLM mirrors the published score view for FACTS Parametric. DeepSeek V4 Pro Base leads the public snapshot at 62.6% , followed by DeepSeek V4 Flash Base (33.9%). BenchLM does not use these results to rank models overall.

2 modelsKnowledgeCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (2 models)

Score
1
DeepSeek V4 Pro BaseDeepSeek · Open weight
62.6%
2
DeepSeek V4 Flash BaseDeepSeek · Open weight
33.9%

About FACTS Parametric

Year

2026

Tasks

Parametric factual recall

Format

Exact match

Difficulty

Factual accuracy focused

BenchLM stores FACTS Parametric as a display-only provider-table row when exact values are published in DeepSeek-V4 evaluations.

BenchLM freshness & provenance

Version

FACTS Parametric 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does FACTS Parametric measure?

A parametric factuality benchmark reported in DeepSeek-V4 base-model evaluations.

Which model scores highest on FACTS Parametric?

DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 62.6% on FACTS Parametric.

How many models are evaluated on FACTS Parametric?

2 AI models have been evaluated on FACTS Parametric on BenchLM.

Compare Top Models on FACTS Parametric

Last updated: July 23, 2026 · BenchLM version FACTS Parametric 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.