Benchmark Almanac

DeepSeek

Best on the Capabilities Index DeepSeek V4.1 Flash 1017 159.4
41 models 22 model cards read deepseek.com

How does DeepSeek stack up?

Every model on Epoch AI's Capabilities Index by release date, with DeepSeek's in color.

50 100 150 2023 2024 2025 2026 2027 DeepSeek V4.1 Flash 1017 DeepSeek-V4-Flash 50 100 150 2023 2024 2025 2026 2027 DeepSeek V4.1 Flash 1017 DeepSeek-V4-Flash

Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)

DeepSeek's best models

DeepSeek Oct 2026

DeepSeek V4.1 Flash 1017

Open weights Mid-size

159.4 #22 of 256
Epoch Capabilities Index
Self-Reported Index 165.8 #13 of 404
  • NL2Repo-Bench 68.2% #1 /30
  • MultiChallenge 74.9% #5 /42
  • Terminal-Bench 4.0 40% #14 /40
DeepSeek Sep 2026

DeepSeek V4.1 Flash

Open weights Mid-size

156.7 #34 of 256
Epoch Capabilities Index
Self-Reported Index 157.6 #45 of 404
  • MMMU-Pro 56.5% #72 /90
  • NL2Repo-Bench 65.4% #2 /30
  • LongBench v2 45.2% #29 /35
DeepSeek Aug 2026

DeepSeek V4 Pro 0813

Open weights Flagship

155.9 #41 of 256
Epoch Capabilities Index
Self-Reported Index 159.9 #31 of 404
  • NL2Repo-Bench 61.5% #4 /30
  • Terminal-Bench 4.0 6.67% #35 /40
  • GPQA Diamond 91.7% #32 /229
DeepSeek Jul 2026

DeepSeek V4 Flash 0731

Open weights Mid-size

154.4 #51 of 256
Epoch Capabilities Index
Self-Reported Index 155.0 #60 of 404
  • NL2Repo-Bench 54.2% #12 /30
  • GPQA Diamond 91% #36 /229
  • Toolathlon-Verified 70.7% #9 /25
DeepSeek Apr 2026

DeepSeek-V4-Pro

Open weights Flagship

150.2 #69 of 256
Epoch Capabilities Index
Self-Reported Index 152.7 #77 of 404
  • SWE-bench Verified 77.6% #6 /32
  • DeepSWE 62.8% #14 /28
  • Agents' Last Exam 12.4% #23 /31
DeepSeek Apr 2026

DeepSeek-V4-Flash

Open weights

146.8 #86 of 256
Epoch Capabilities Index
Self-Reported Index 150.0 #93 of 404
  • DeepSWE 53.3% #20 /28
  • AutomationBench 18.1% #18 /42
  • Toolathlon 48.2% #10 /50

What benchmarks does DeepSeek mention most?

Here are the 28 benchmarks DeepSeek mentions most in its launch posts.

Source: Labs’ launch posts, read by Benchmark Almanac

Model cards

DateModelDocumentBenchmarks
Oct 17, 2026 DeepSeek V4.1 Flash 1017 DeepSeek-V4.1-Flash-1017 model card 11
Sep 10, 2026 DeepSeek V4.1 Flash DeepSeek-V4.1-Flash model card 37
Aug 21, 2026 DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-Vision-Exp model card (Hugging Face) 10
Aug 13, 2026 DeepSeek V4 Pro 0813 DeepSeek-V4-Pro-0813 model card 10
Jul 31, 2026 DeepSeek V4 Flash 0731 DeepSeek-V4-Flash-0731 model card 9
Apr 24, 2026 DeepSeek-V4-Flash DeepSeek-V4-Flash model card (Hugging Face) 21
Apr 24, 2026 DeepSeek-V4-Pro DeepSeek-V4-Pro model card 43
Jan 28, 2026 DeepSeek-OCR 2 DeepSeek-OCR 2: Visual Causal Flow (technical report and repository) 1
Dec 1, 2025 DeepSeek-V3.2 DeepSeek-V3.2 technical report, Table 2 18
Nov 27, 2025 DeepSeekMath-V2 DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning (model card) 3
Sep 29, 2025 DeepSeek-V3.2-Exp DeepSeek-V3.2-Exp model card 14
Sep 22, 2025 DeepSeek-V3.1-Terminus DeepSeek-V3.1-Terminus model card 12
Aug 21, 2025 DeepSeek-V3.1 DeepSeek-V3.1 model card 16
May 28, 2025 DeepSeek-R1 May 2025 DeepSeek-R1-0528 model card 16
Apr 30, 2025 DeepSeek-Prover-V2-671B DeepSeek-Prover-V2 model card (Hugging Face) 3
Mar 24, 2025 DeepSeek-V3 DeepSeek-V3-0324 model card 5
Jan 27, 2025 Janus-Pro-7B Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling (GitHub README and tech report) 9
Jan 20, 2025 DeepSeek-R1 DeepSeek-R1 model card 20
Dec 26, 2024 DeepSeek-V3 DeepSeek-V3 model card 48
Sep 5, 2024 DeepSeek-V2.5 Sep 2024 DeepSeek-V2.5 model card 11
May 7, 2024 DeepSeek-V2 (MoE-236B, May 2024) DeepSeek-V2 model card 13
Nov 29, 2023 DeepSeek LLM 67B DeepSeek LLM GitHub README 12

Every DeepSeek model