Skip to main content

Benchmark profile

TriviaQA

A reading and trivia question-answering benchmark reported in DeepSeek-V4 base-model evaluations.

Data verified

Benchmark score on TriviaQA — July 23, 2026

BenchLM mirrors the published score view for TriviaQA. DeepSeek V4 Pro Base leads the public snapshot at 85.6% , followed by DeepSeek V4 Flash Base (82.8%). 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
85.6%
2
DeepSeek V4 Flash BaseDeepSeek · Open weight
82.8%

About TriviaQA

Year

2026

Tasks

Trivia and reading-comprehension QA

Format

Exact match

Difficulty

General factual QA

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

BenchLM freshness & provenance

Version

TriviaQA 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 TriviaQA measure?

A reading and trivia question-answering benchmark reported in DeepSeek-V4 base-model evaluations.

Which model scores highest on TriviaQA?

DeepSeek V4 Pro Base by DeepSeek currently leads with a score of 85.6% on TriviaQA.

How many models are evaluated on TriviaQA?

2 AI models have been evaluated on TriviaQA on BenchLM.

Last updated: July 23, 2026 · BenchLM version TriviaQA 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.