DeepSeek

DeepSeek V3.1

Announced Aug 21, 2025

Thinking and ordinary answers

What could it do?

DeepSeek combined thinking and nonthinking modes.

What changed?

An updated V3 model.

WHY IT MATTERED

One model could serve both modes.

Where it fell short

Historical version; API aliases can change.

Sources checked Oct 7, 2026

Release facts were checked against the sources below. Performance claims belong to the developers; we have not independently tested these models.

Developer announcement or release log

Benchmark results

EPOCH AI CAPABILITY ESTIMATE

139.9index points

Tested variant: DeepSeek-V3.1Source interval: 135.4 to 143.2Variant date in source: Aug 21, 2025

A benchmark estimate, not a percentage or capability multiplier. Reasoning settings are not specified in this source table. Historical estimates can change in later snapshots.

Epoch AI methodology ↗Download the source snapshotChecked Oct 7, 2026 · CC BY 4.0

PUBLISHED BENCHMARK RESULT

1416rating points

Tested: deepseek-v3.1-thinkingText Arena Overall · October 8, 2026Reported interval: 1409 to 142311,458 votes

One explicitly named variant per release. Scores come from the same Overall snapshot; preliminary entries and reported intervals are preserved. These are current ratings of earlier variants, not their launch day ratings.

Source: Text Arena ↗Download selected resultsChecked Oct 8, 2026

Understand the benchmarks Find this release on the chart