ModelsIndexCompareBest forBenchmarksStatusPricingAPI

DeepSeek V3.1

DeepSeek·Operational·Released 2025-08-21text
Context128k
Max output-
Input / 1M-
Output / 1M-
Cached in-
Benchmarks18

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

SimpleBench (SimpleBench)#59/7340% ↗
WeirdML (Håvard Tveit Ihle)#75/9238.4% ↗
LMArena Elo#89/1411417.1 ↗
Aider-Polyglot (thinking)76.3% ↗
AIME 2024 (thinking)93.1% ↗
AIME 2025 (thinking)88.4% ↗
BrowseComp#23/2330% ↗
GPQA-Diamond (thinking)80.1% ↗
HMMT 2025 (thinking)84.2% ↗
Humanity's Last Exam (Python + Search)29.8% ↗
Humanity's Last Exam (thinking, text-only)15.9% ↗
LiveCodeBench (2408-2505) (thinking)74.8% ↗
MMLU-Pro (thinking)#1/384.8% ↗
MMLU-Redux (thinking)#1/393.7% ↗
SimpleQA (search agent)93.4% ↗
SWE Verified (Agent mode)66% ↗
SWE-bench Multilingual (Agent mode)54.5% ↗
Terminal-bench (Terminus 1 framework)31.3% ↗

Compare

vs Gemini 4 Argonvs GPT-6.1 Solvs Claude Sonnet 5.5vs Muse Spark 1.3vs GPT-6 Solvs GPT-6 Lunavs Claude Opus 5.5vs GPT-6 Astra

More from DeepSeek

DeepSeek V4.1 FlashDeepSeek V4 ProDeepSeek V3.2DeepSeek R1DeepSeek V3DeepSeek V4 Flash

DeepSeek V3.1 FAQ

What is DeepSeek V3.1?
DeepSeek V3.1 is a large language model from DeepSeek, released on August 21, 2025. It accepts text input.
When was DeepSeek V3.1 released?
DeepSeek released DeepSeek V3.1 on August 21, 2025.
What is DeepSeek V3.1's context window?
DeepSeek V3.1 has a 128K-token context window.
How does DeepSeek V3.1 score on benchmarks?
DeepSeek V3.1 has 18 cited benchmark scores, including SimpleBench (SimpleBench) 40%, WeirdML (Håvard Tveit Ihle) 38.4% and LMArena Elo 1417.1 Elo. Each score links to its source.

Access DeepSeek V3.1 and every other model through one endpoint with automatic failover: Respan gateway.