Language modelActive

DeepSeek-V3.1

DeepSeek

Released: August 21, 2025
Data date: September 8, 2026
Predecessor: DeepSeek-V3 0324
Successor: DeepSeek-V3.1 Terminus

Price: $0.27 · $1
Input · Output / 1M tokens
Input: Text
Output: Text

New in DeepSeek-V3.1 are separate thinking and non-thinking modes. The checkpoint remains a 671-billion-parameter mixture-of-experts model with 37 billion active parameters and a 128,000-token context window.

V3.1 follows DeepSeek-V3 0324 and is stabilized by DeepSeek-V3.1 Terminus. In the API, deepseek-chat and deepseek-reasoner represent separate usage modes even though they refer to one checkpoint.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	671BSource
Active parameters	37BSource
Context window	128,000 tokensSource
License	MITSource
Parameters	671 BSource
Active parameters	37 BSource
Architecture	MoE hybrid thinking/non-thinkingSource
Input	TextSource
Output	TextSource
Reasoning mode	thinking, non-thinkingSource
Tool calling	YesSource
Training tokens	630B pre-training plus 209B continued training (Token counts describe extension/continued-training data, not a full pretraining corpus)Source

Published benchmarks

CorpFin v2

Overall

1.Claude Opus 573.19%

2.Claude Fable 571.83%

3.Kimi K371.56%

4.Inkling Small69.62%

5.Inkling68.57%

6.Grok 4.368.53%

7.GPT-5.568.42%

8.Kimi K2.568.26%

9.MiniMax M368.1%

10.Grok 4.567.41%

11.Claude Sonnet 566.98%

12.Kimi K2.666.74%

13.Claude Opus 4.866.71%

14.Gemini 3 Flash Preview66.43%

15.Grok 4.666.16%

16.GLM-5.266.12%

17.Claude Opus 4.766.08%

18.Qwen 3.8 Max 090265.85%

19.Nemotron 3 Ultra65.46%

20.Claude Sonnet 4.665.31%

20.GPT-5.6 Terra65.31%

22.GPT-5.465.27%

23.Gemini 3.5 Flash64.69%

24.Gemini 3.1 Pro Preview64.49%

25.GLM-5.164.45%

26.GPT-5.6 Sol64.38%

27.GPT-5.6 Luna64.22%

28.Qwen 3.7 Max63.71%

29.Grok 4.20 Reasoning63.68%

30.Gemini 3.6 Flash63.33%

31.GPT-4.163.05%

32.GLM-562.9%

33.Qwen 3.6 27B62.32%

34.Ling 3.0 Flash61.93%

35.MiMo-V2.5-Pro61.42%

36.DeepSeek-V4-Pro61.38%

37.Claude Opus 4.561.31%

38.GPT-5.4 nano61.19%

38.MiniMax M2.761.19%

40.GPT-561.07%

41.Mistral Large 361.03%

42.GLM-4.560.96%

43.GPT-5.4 mini60.92%

44.Claude Sonnet 4.560.8%

44.Gemini 2.5 Pro60.8%

46.Gemini 3.5 Flash-Lite60.68%

47.Kimi K2 Thinking60.57%

48.Claude Haiku 4.560.3%

49.GPT-5 mini60.18%

50.MiMo-V2.559.91%

51.o359.71%

52.MiniMax M2.559.6%

53.Gemini 3.1 Flash-Lite59.36%

54.o4-mini58.97%

55.MiniMax M2.158.9%

56.Mistral Medium 3.558.78%

57.GPT OSS 120B58.24%

58.GPT-4.1 mini57.93%

59.GLM-4.656.84%

60.DeepSeek-V3 032454.74%

61.Trinity Large Thinking54.66%

62.Nemotron 3.5 Lightning54.24%

63.DeepSeek-R154.12%

64.GPT OSS 20B53.15%

65.DeepSeek-V352.49%

66.DeepSeek-V3.151.48%

67.Kimi K2 071150.39%

68.DeepSeek-V3.247.94%

69.Llama 4 Scout46.78%

70.GLM-4.746.39%

71.Command A45.96%

72.GPT-4o mini45.46%

73.o3-mini45.3%

74.Mistral Small 3.144.17%

75.GPT-4.1 nano42.08%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-corp-fin-v2:2:overall
Metric: accuracy
Scale: 0-100
Participants: 75
Methodology and context: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Latency in seconds: 62.999. Cost per task in USD: 0.037369. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-09-29-83186cfafe52. Source payload hash: 83186cfafe526f0b8fe2ae86af05e8209fe799c8bfa48292ef1fef5db66650ee. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Agent tasks

Agent Poker Bench

Overall

1.GPT-51,103.18 rating

2.Gemini 3 Flash Preview1,100.21 rating

3.DeepSeek-V3.11,058.23 rating

4.Claude Sonnet 4.51,055.5 rating

5.Claude Opus 4.51,033.38 rating

6.Gemini 2.5 Pro1,032.6 rating

7.GPT OSS 120B1,015.33 rating

8.Kimi K2 Thinking1,011.63 rating

9.GLM-4.6945.76 rating

higher is betterAs of September 29, 2026Scale: 0 rating - 1,103.18 rating

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-poker-agent:1:overall
Metric: TrueSkill rating
Scale: No upper bound is documented. The chart spans the recorded values and zero.
Participants: 9
Methodology and context: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2025-12-23. Latency in seconds: 3.9977358921550272. Standard error: 0. Cost per task in USD: 0.007085498012100262. Source ID: vals-ai. Evidence capture ID: vals-poker_agent-2026-09-29-f29b75137483. Source payload hash: f29b751374830275dd1fba4c8a4f029b69433858ae99420aa90befe3093d0096. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Terminal-Bench 2.0

Overall

1.GPT-5.573.2%

2.Claude Opus 4.870.04%

3.Claude Opus 4.768.54%

4.Gemini 3.1 Pro Preview67.42%

4.Gemini 3.5 Flash67.42%

6.GPT-5.3-Codex64.05%

7.Claude Sonnet 4.659.55%

8.Qwen 3.7 Max59.18%

9.Claude Opus 4.558.43%

9.GPT-5.458.43%

11.Kimi K2.657.3%

12.DeepSeek-V4-Pro56.18%

13.GLM-5.153.93%

14.Gemini 3 Flash Preview51.69%

15.GLM-549.44%

16.MiniMax M2.747.19%

17.MiniMax M346.07%

18.GPT-5.4 mini44.94%

18.Qwen 3.6 27B44.94%

20.Grok 4.343.45%

21.MiniMax M2.541.57%

22.Grok 4.20 Reasoning40.45%

22.Kimi K2.540.45%

24.GPT-5.4 nano39.89%

25.Gemma 4 31B39.33%

26.GLM-4.738.2%

27.GPT-537.08%

27.Kimi K2 Thinking37.08%

27.MiniMax M2.137.08%

30.DeepSeek-V3.234.83%

31.Gemini 2.5 Pro30.34%

31.Mistral Medium 3.530.34%

33.GLM-4.628.09%

34.GPT-5 mini26.97%

35.Kimi K2 071125.84%

36.Gemini 3.1 Flash-Lite24.72%

37.DeepSeek-V3.122.47%

38.GPT OSS 120B19.1%

39.Trinity Large Thinking17.98%

40.Mistral Small 416.85%

41.GPT-4.114.61%

42.Mistral Large 38.99%

43.Command A2.25%

higher is betterAs of September 29, 2026Scale: 0% - 100%

Source: Vals AI

CC BY 4.0

gradually.ai

Methodology and context

Comparison cohort: vals-terminal-bench-2:2.0:overall
Metric: accuracy
Scale: 0-100
Participants: 43
Methodology and context: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-06-04. Latency in seconds: 837.847. Cost per task in USD: 0.501536. Source ID: vals-ai. Evidence capture ID: vals-terminal-bench-2-2026-09-29-020c4135b825. Source payload hash: 020c4135b82502d8cc0324b9b7d9474024a86da8f4770c78743bd13103cdfa0c. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source: Vals AI

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

CaseLaw v2: Overall (Show measurement, test conditions, and source)

Source value: 53.912
Score: 53.912
Metric: accuracy
Unit: %
Benchmark version: 2
Category: legal
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-case-law-v2:2:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-05-04. Latency in seconds: 40.682. Cost per task in USD: 0.016723. Source ID: vals-ai. Evidence capture ID: vals-case_law_v2-2026-09-29-cd282b756eb4. Source payload hash: cd282b756eb41a617c01694c5ed3b3d1872a9f417d8aac675370f4943c6c7c63. Parser version: vals-astro-v2. Imported at: 2026-09-29
Context: The source dataset marks this benchmark as archived. The result remains visible as historical evidence and is not interchangeable with an active leaderboard.

Source Vals AI

MMLU-Redux (Show measurement, test conditions, and source)

Source value: 91.8
Score: 91.8
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

MMLU-Pro (Show measurement, test conditions, and source)

Source value: 83.7
Score: 83.7
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

GPQA (Show measurement, test conditions, and source)

Source value: 74.9
Score: 74.9
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

LiveCodeBench (Show measurement, test conditions, and source)

Source value: 56.4
Score: 56.4
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

Aider-Polyglot (Show measurement, test conditions, and source)

Source value: 68.4
Score: 68.4
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

SWE Verified (Show measurement, test conditions, and source)

Source value: 66
Score: 66
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

SWE multilingual (Show measurement, test conditions, and source)

Source value: 54.5
Score: 54.5
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

Terminal-bench (Show measurement, test conditions, and source)

Source value: 31.3
Score: 31.3
Metric: percent
Unit: %
Category: reasoning
Direction: Higher is better
Source type: vendor-reported
Evaluator: DeepSeek V3.1 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. table column V3.1; thinking/non-thinking and tool settings are distinct in source

Source DeepSeek V3.1 model card

Recorded measurement details

CorpFin v2: Overall (Show measurement, test conditions, and source)

Source value: 51.476
Score: 51.476
Metric: accuracy
Unit: %
Benchmark version: 2
Category: finance
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-corp-fin-v2:2:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-08-12. Latency in seconds: 62.999. Cost per task in USD: 0.037369. Source ID: vals-ai. Evidence capture ID: vals-corp_fin_v2-2026-09-29-83186cfafe52. Source payload hash: 83186cfafe526f0b8fe2ae86af05e8209fe799c8bfa48292ef1fef5db66650ee. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

Agent Poker Bench: Overall (Show measurement, test conditions, and source)

Source value: 1058.2325209691314
Score: 1058.2325209691314
Metric: TrueSkill rating
Unit: rating
Benchmark version: 1
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-poker-agent:1:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2025-12-23. Latency in seconds: 3.9977358921550272. Standard error: 0. Cost per task in USD: 0.007085498012100262. Source ID: vals-ai. Evidence capture ID: vals-poker_agent-2026-09-29-f29b75137483. Source payload hash: f29b751374830275dd1fba4c8a4f029b69433858ae99420aa90befe3093d0096. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

Terminal-Bench 2.0: Overall (Show measurement, test conditions, and source)

Source value: 22.472
Score: 22.472
Metric: accuracy
Unit: %
Benchmark version: 2.0
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: vals-terminal-bench-2:2.0:overall
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-09-29
Methodology: Source model ID: fireworks/deepseek-v3p1. Source model name: DeepSeek-V3.1. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-06-04. Latency in seconds: 837.847. Cost per task in USD: 0.501536. Source ID: vals-ai. Evidence capture ID: vals-terminal-bench-2-2026-09-29-020c4135b825. Source payload hash: 020c4135b82502d8cc0324b9b7d9474024a86da8f4770c78743bd13103cdfa0c. Parser version: vals-astro-v2. Imported at: 2026-09-29

Source Vals AI

Page 1 of 2

Predecessor and successor

Sources and data date

Type	Evidence and data date
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · DeepSeek V3.1 model card (retrieved September 8, 2026) · DeepSeek-V3.1 model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · DeepSeek V3.1 model card (retrieved September 8, 2026) · DeepSeek-V3.1 model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	release-date Original wording No exact release-date field in card.
Not found in the inspected sources	knowledge-cutoff Original wording No cutoff stated.
Additional source	Model metadata
Additional source	Context window data · DeepSeek official website · Editorial description reviewed October 2, 2026
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Vals AI (retrieved September 29, 2026)
Additional source	Artificial Analysis (retrieved September 8, 2026)
Additional source	DeepSeek-V3.1 announcement · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0
Additional source	DeepSeek API changelog (2026-09-22)
Additional source	DeepSeek-V3.1-Terminus model card (2026-09-09)

DeepSeek-V3.1

Specifications and access

Published benchmarks

CorpFin v2

Agent tasks

Agent Poker Bench

Terminal-Bench 2.0

Measurements without matching peer values

Recorded measurement details

Our tests

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date