Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

FACTS Parametric

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

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on FACTS Parametric — September 15, 2026

We mirror 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%). We do not use these results to rank models overall.

1Open weights

DeepSeek V4 Pro Base

DeepSeek

62.6%
Context 1M
2Open weights

DeepSeek V4 Flash Base

DeepSeek

33.9%
Context 1M

2 modelsKnowledgeCurrentDisplay onlyUpdated September 15, 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.

DeepSeek-V4 Technical Report

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.

Last updated: September 15, 2026 · BenchLM version FACTS Parametric 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.