DeepSeek-V3.1

DeepSeek-V3.1 places in the top three on AMO-Bench.

DeepSeek Released 21 Aug 2025 Family DeepSeek-V3 The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

DeepSeek Aug 2025

Open weights Flagship

139.8 #126 of 271

Epoch Capabilities Index

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
SimpleQA	93.4%	#4 of 59	Model card
Vectara Hallucination Leaderboard (2025 dataset)	5.50%	#19 of 104	Official leaderboard
SuperGPQA	59.3%	#11 of 58	Official leaderboard
MMLU-Pro	84.8%	#32 of 151	Model card
MMLU-Redux	93.7%	#9 of 38	Model card
LMArena (Elo)	1,417	#107 of 333	Official leaderboard
Vectara Hallucination Leaderboard (HHEM)	5.50%	#49 of 148	Official leaderboard
ECLeKTic	19%	#16 of 35	Official leaderboard
Creative Writing v3	69.9	#56 of 120	Official leaderboard
HELM Arabic Enterprise	65.9	#11 of 23	Official leaderboard
Longform Creative Writing (EQ-Bench)	62.3	#59 of 119	Official leaderboard
Humanity's Last Exam	29.8%	#77 of 147	Model card
Phare	64.8%	#34 of 62	Official leaderboard
HELM Arabic	77.9	#16 of 28	Official leaderboard
Wer wird Millionär? LLM Benchmark	1111.0	#48 of 76	Official leaderboard
SimpleQA Verified	24.3%	#36 of 56	Official leaderboard
MultiNRC	23.6%	#26 of 38	Official leaderboard
Fiction.LiveBench	52.8%	#40 of 57	Epoch AI
Global MMLU Lite	80.4%	#32 of 43	Official leaderboard
MultiChallenge	46.1%	#30 of 35	Official leaderboard

Benchmark	Score	Rank	Source
AIME 2024	93.1%	#7 of 87	Model card
AMO-Bench	47.6%	#3 of 21	Official leaderboard
ForecastBench	60.6	#24 of 86	Official leaderboard
GPQA Diamond	80.1%	#111 of 284	Model card
AIME 2025	88.4%	#58 of 143	Model card
DTBench	71.1%	#76 of 178	Official leaderboard
BRUMO 2025	90%	#25 of 42	Official leaderboard
SMT 2025	84%	#24 of 40	Official leaderboard
CMIMC 2025	82.5%	#20 of 33	Official leaderboard
HMMT 2025	84.2%	#30 of 49	Model card
SimpleBench	40%	#69 of 100	Official leaderboard
CORE-Bench	20%	#12 of 17	Official leaderboard
PHYBench	16.6%	#21 of 28	Official leaderboard
General365	48.1%	#19 of 23	Official leaderboard
MathArena (Apex, IMO, USAMO)	0.52%	#43 of 47	Official leaderboard

Benchmark	Score	Rank	Source
Aider Polyglot	76.3%	#5 of 29	Model card
LiveCodeBench	74.8%	#19 of 73	Model card
Codeforces rating	2,091	#20 of 41	Model card
SWE-bench Verified	66%	#94 of 150	Model card
SWE-fficiency	4.32%	#12 of 17	Official leaderboard
WeirdML	38.4%	#85 of 112	Official leaderboard
SWE-bench Multilingual	54.5%	#65 of 70	Model card

Benchmark	Score	Rank	Source
Step Race	4	#12 of 59	Official leaderboard
Meta Agents Research Environments (ARE) / Gaia2	21.9%	#5 of 13	Official leaderboard
Agent Poker Bench	1,058	#7 of 17	Official leaderboard
CompileBench	80%	#9 of 20	Official leaderboard
SnakeBench	23	#96 of 183	Official leaderboard
MCP-Universe	22.1%	#21 of 30	Official leaderboard
MCPMark	16.7%	#20 of 28	Official leaderboard
GAIA	27.9%	#41 of 57	Official leaderboard
BrowseComp-ZH	49.2%	#14 of 17	Model card
Terminal-Bench	31.3%	#19 of 22	Model card
BrowseComp	30%	#73 of 77	Model card

Benchmark	Score	Rank	Source
ProfBench	46.6%	#38 of 72	Official leaderboard
StockBench	1.10%	#8 of 13	Official leaderboard
CaseLaw v2	53.9%	#39 of 53	Official leaderboard
CorpFin v2	51.5%	#92 of 119	Official leaderboard
PRBench	37.6%	#38 of 44	Official leaderboard
FailureSensorIQ	36.6%	#23 of 24	Official leaderboard

Benchmark	Score	Rank	Source
BrowseSafe++	75.2%	#10 of 15	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	39.8%	#56 of 71	Official leaderboard
FORTRESS	60.5%	#62 of 66	Official leaderboard

Benchmark	Score	Rank	Source
Conceptual Reasoning Index	39.9	#98 of 149	Official leaderboard
ACCoRD	55.5	#103 of 150	Official leaderboard
LMCA	24.3%	#97 of 139	Epoch AI

DeepSeek's models in color, against every other model on the Epoch Capabilities Index, by release date.

The benchmarks the lab chose to headline, with the scores it gave.