Compare Models

DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is an open-weight model from DeepSeek, released October 17, 2026. It ranks #10 of 29 models on the Vals Index with 61.26%. Its best result is #7 of 78 on Tax Agent Bench.

Release Date: Oct 17, 2026

Developer DeepSeek  🇨🇳
Context Window 1M
Max Output Tokens 384k
Token Costs (in/out) $0.30/1.20
Weights Open
Input Modalities

Accuracy

61.26 % ± 1.05

Cost / Test (Vals Index)

$ 0.657

Latency

39 min 55 s

Vals Index
BenchmarksAccuracyRankings
Vals Index

61.26%

±1.05
10/29
Vals Finance Index

60.89%

±1.47
8/33
Vals Legal Index

71.86%

±1.82
10/30
Code Migration v1.1

67.52%

±2.76
7/28
EMB v1.1

69.17%

±2.40
18/35
Finance Agent v2.1

62.93%

±2.03
13/33
Legal Research Bench

45.19%

±3.46
19/87
Tax Agent Bench

44.35%

±3.57
7/78
Vibe Code Bench v1.1

87.73%

±2.75
12/121
HLAB-Vals-1.1

14.17%

±2.79
10/30
Terminal-Bench 4.0

31.82%

±2.62
21/57
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : DeepSeek
Temperature: 1
Top P: 1
Top K: Default
Max Output Tokens: 384,000
Reasoning Effort: max

Compared with

DeepSeek V4.1 Flash 1017 vs GPT-6 Sol 4 shared benchmarks DeepSeek V4.1 Flash 1017 vs GPT-5.6 Sol 4 shared benchmarks DeepSeek V4.1 Flash 1017 vs Muse Spark 1.3 Max 4 shared benchmarks DeepSeek V4.1 Flash 1017 vs MiMo V2.6 Pro 11 shared benchmarks DeepSeek V4.1 Flash 1017 vs Claude Opus 4.8 4 shared benchmarks DeepSeek V4.1 Flash 1017 vs Grok 4.7 11 shared benchmarks DeepSeek V4.1 Flash 1017 vs Gemini 3.8 Flash 11 shared benchmarks DeepSeek V4.1 Flash 1017 vs Claude Haiku 5.5 11 shared benchmarks DeepSeek V4.1 Flash 1017 vs GPT-6.1 Sol 11 shared benchmarks