Skip to content
Model Pareto

DeepSeek V4.1 Flash 1017 vs DeepSeek V4.1 Flash

DeepSeek V4.1 Flash 1017 scores higher than DeepSeek V4.1 Flash in both shared categories. Both cost about $0.52 per million tokens, blended 3:1 input:output.
DeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash
Focus

Coding: quality vs price

Compared models are ringed; the other 131 ranked here are greyed.

Lower price is better. Pareto frontier: Nex-N2.5-Mini, Nex-N2.5-Pro, MiMo-V2.6-Flash, Ternary Bonsai 2 27B, MiMo-V2.6-Pro, Kimi K3.1 Pro, Claude Opus 5.5. 43 models are not plotted: Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

43 models with no price data — shown in the strip at the left edge

Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • DeepSeek V4.1 Flash 1017
    Quality
    74.1
    Rank
    #16/133
    Price
    $0.52/M tok
    Speed
    —
    In$0.30▾Out$1.20▾/M tok

    vs DeepSeek V4.1 Flash: +6.0 quality · 1× price

  • DeepSeek V4.1 Flash
    Quality
    68.2
    Rank
    #28/133
    Price
    $0.52/M tok
    Speed
    232tok/s
    In$0.30▾Out$1.20▾/M tok

    vs DeepSeek V4.1 Flash 1017: −6.0 quality · 1× price

Overview

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
Lab
DeepSeek
DeepSeek
Released
Oct 17, 2026
Sep 10, 2026
Weights
Open
Open
Input price
$/M tok
$0.30Best
$0.30Best
Output price
$/M tok
$1.20Best
$1.20Best
Blended price
$/M tok · 3:1 in:out
$0.525Best
$0.525Best
Output speed
tok/s
—
232
Context
tokens
1MBest
1MBest

Quality by category

0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
Coding
74.1±4.7Best
#16/133Mixed
68.2±4.7
#28/133Mixed
Writing & chat
Not ranked
65.4±4.3
#38/160Verified
Vision
Not ranked
55.4±4.8
#49/97Verified
Hard reasoning
81.9±5.1Best
#19/213Verified
75.6±4.0
#35/213Mixed
Agents
Not ranked
79.9±7.8
#18/186Verified

Coding benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
SWE-bench Verified
day 0
~#2/20~88.2%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2DeepSeek V4.1 Flash 1017Estimated88.2%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
~#3/20~83.4%Estimated
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3DeepSeek V4.1 FlashEstimated83.4%
  4. #3Beam 1.0 501B A23B81.6%
estimated from related benchmarks
SWE-bench Pro (Public)
day 0
~#5/23~70.6%Estimated
  1. #1Claude Opus 5.589.9%
  2. #4Claude Opus 579.2%
  3. ~#5DeepSeek V4.1 Flash 1017Estimated70.6%
  4. #5Intern-S2-397B68.5%
estimated from related benchmarks
~#7/23~65.7%Estimated
  1. #1Claude Opus 5.589.9%
  2. #6Beam 1.0 501B A23B66.1%
  3. ~#7DeepSeek V4.1 FlashEstimated65.7%
  4. #7Hy4 preview65.7%
estimated from related benchmarks
DeepSWE v1.1
day 0
#2/4277.0%BestLab-reported
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
  3. #2Muse Wonder Full77.0%
huggingface.co · 2026-10-17
#5/4274.2%Lab-reported
  1. #1Gemini 4 Argon78.8%
  2. #4Muse Wonder75.8%
  3. #5DeepSeek V4.1 Flash74.2%
  4. #6MiniMax-M3.1-Flash73.7%
huggingface.co · 2026-09-10
Terminal-Bench 4.0
day 0
#16/9833.8%BestVerified
  1. #1Kimi K3.1 Pro67.2%
  2. #15MiMo-V2.6-Pro34.8%
  3. #16DeepSeek V4.1 Flash 101733.8%
  4. #17Ling 3.1 Flash33.3%
artificialanalysis.ai · 2026-10-24
#22/9826.8%Verified
  1. #1Kimi K3.1 Pro67.2%
  2. #20GLM-5.3 Flash32.8%
  3. #22DeepSeek V4.1 Flash26.8%
  4. #22Mistral Large 426.8%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#6/28~88.8%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #5Nemotron 3 Ultra89.0%
  3. ~#6DeepSeek V4.1 Flash 1017Estimated88.8%
  4. #6Beam 1.0 501B A23B88.3%
estimated from related benchmarks
~#11/28~81.5%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #10Ternary Bonsai 27B82.8%
  3. ~#11DeepSeek V4.1 FlashEstimated81.5%
  4. #11Gemma 4 31B80.0%
estimated from related benchmarks
SciCode
third-party
#22/11755.9%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #21Claude Opus 556.4%
  3. #22DeepSeek V4.1 Flash 101755.9%
  4. #23DeepSeek V4.1 Flash NVFP455.8%
artificialanalysis.ai · 2026-10-24
#39/11751.9%Verified
  1. #1Claude Opus 5.566.9%
  2. #37Qwen3.8 Max (0902)52.1%
  3. #39DeepSeek V4.1 Flash51.9%
  4. #40GLM-5.3 Flash51.6%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
#15/2346.3Verified
  1. #1Claude Opus 5.561.7
  2. #14Grok 4.746.6
  3. #15DeepSeek V4.1 Flash 101746.3
  4. #16Muse Spark 1.345.7
artificialanalysis.ai · 2026-10-24
#12/2347.3BestVerified
  1. #1Claude Opus 5.561.7
  2. #11GLM-5.348.9
  3. #12DeepSeek V4.1 Flash47.3
  4. #13Grok 4.647.0
artificialanalysis.ai · 2026-10-24
Benchmarks in other categories (4)

Writing & chat benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
IFBench
day 0
—
~#29/138~72.0%Estimated
  1. #1MiniMax-M382.9%
  2. #28Gemma 4 26B A4B72.4%
  3. ~#29DeepSeek V4.1 FlashEstimated72.0%
  4. #29Nemotron 3 Super 120B A12B71.5%
estimated from related benchmarks
MMMLU
day 0
—
~#2/5~90.9%Estimated
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2DeepSeek V4.1 FlashEstimated90.9%
  3. #2Gemma 4 31B88.4%
estimated from related benchmarks
LMArena Text, Non-English (Elo)
third-party
—
#16/561459Verified
  1. #1Gemini 4 ArgonFew votes1512
  2. #15MiMo-V2.6-Pro1461
  3. #16DeepSeek V4.1 Flash1459
  4. #17GPT-5.6 Terra1456
lmarena.ai · 2026-10-02
LMArena Text (Elo)
third-party
—
#16/561474Verified
  1. #1Gemini 4 Argon1525
  2. #15GLM-5.3 Flash1475
  3. #16DeepSeek V4.1 Flash1474
  4. #17GPT-5.6 Terra1466
lmarena.ai · 2026-10-02
EQ-Bench Creative Writing v3 (Elo)
third-party
—
#20/251540Verified
  1. #1GPT-6 Astra2173
  2. #19Gemini 3.5 Flash-Lite1559
  3. #20DeepSeek V4.1 Flash1540
  4. #21Gemini 3.1 Pro1491
eqbench.com · 2026-09-24

Vision benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
MMMU
day 0
—
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2DeepSeek V4.1 FlashEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
—
#28/8777.0%Verified
  1. #1Claude Opus 5.587.7%
  2. #26Qwen3.5 397B A17B77.3%
  3. #28DeepSeek V4.1 Flash77.0%
  4. #29Intern-S2-Preview (35B-A3B)76.9%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
—
~#8/12~79.4%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. #7Nemotron 3.5 Super VL NVFP479.9%
  3. ~#8DeepSeek V4.1 FlashEstimated79.4%
  4. #8Muse Glimmer78.8%
estimated from related benchmarks
OmniDocBench v1.5
third-party
—
~#5/8~85.0%Estimated
  1. #1MiniMax-M391.6%
  2. #4Gemini 3.1 Pro85.3%
  3. ~#5DeepSeek V4.1 FlashEstimated85.0%
  4. #5Claude Haiku 4.579.6%
estimated from related benchmarks
GDP.pdf (AA)
third-party
—
#28/4612.8%Verified
  1. #1Muse Wonder Full32.6%
  2. #27Claude Sonnet 513.2%
  3. #28DeepSeek V4.1 Flash12.8%
  4. #28Inkling12.8%
artificialanalysis.ai · 2026-09-24
Chartography
third-party
—
#20/2311.6%Verified
  1. #1GPT-6 Astra71.0%
  2. #19Grok 4.714.7%
  3. #20DeepSeek V4.1 Flash11.6%
  4. #21Gemini 3.5 Flash-Lite10.2%
surgehq.ai · 2026-09-24

Hard reasoning benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
GPQA Diamond
day 0
~#2/191~95.5%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2DeepSeek V4.1 Flash 1017Estimated95.5%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
#28/19090.9%Lab-reported
  1. #1GPT-6 Astra96.1%
  2. #27Qwen3.8-Omni-Flash91.0%
  3. #28DeepSeek V4.1 Flash90.9%
  4. #29Beam 1.0 501B A23B90.6%
huggingface.co · 2026-09-10
Humanity's Last Exam
day 0
#24/19743.3%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #23Hy4 preview43.4%
  3. #24DeepSeek V4.1 Flash 101743.3%
  4. #25Grok 4.743.1%
artificialanalysis.ai · 2026-10-24
#35/19739.2%Verified
  1. #1Claude Opus 5.561.4%
  2. #34Ling 3.1 Flash39.4%
  3. #35DeepSeek V4.1 Flash39.2%
  4. #36MiniMax-M339.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/33~98.9%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2DeepSeek V4.1 Flash 1017Estimated98.9%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
~#4/33~95.9%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. #3Inkling97.1%
  3. ~#4DeepSeek V4.1 FlashEstimated95.9%
  4. #4Ternary Bonsai 2 27B95.8%
estimated from related benchmarks
AA Intelligence Index
third-party
#16/10045.1BestVerified
  1. #1Claude Opus 5.557.6
  2. #15Qwen3.8 Max (0902)45.4
  3. #16DeepSeek V4.1 Flash 101745.1
  4. #17GLM-5.344.8
artificialanalysis.ai · 2026-10-24
#29/10039.5Verified
  1. #1Claude Opus 5.557.6
  2. #28Qwen3.8 Flash-Next39.8
  3. #29DeepSeek V4.1 Flash39.5
  4. #30Muse Spark Open38.9
artificialanalysis.ai · 2026-09-24

Agents benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash
τ²-bench (Telecom)
day 0
—
~#9/120~93.1%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #8Qwen3.5 122B A10B93.6%
  3. ~#9DeepSeek V4.1 FlashEstimated93.1%
  4. #9Qwen3.7 Plus93.0%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#7/15~80.7%Estimated
  1. #1Kimi K384.8%
  2. #6MiMo-V2.6-Flash80.8%
  3. ~#7DeepSeek V4.1 FlashEstimated80.7%
  4. #7Muse Spark Open80.4%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~#3/5~57.6%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3DeepSeek V4.1 FlashEstimated57.6%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
BrowseComp
day 0
—
~#8/22~86.4%Estimated
  1. #1Atria Dawn Preview92.5%
  2. #7GPT-5.6 Terra87.5%
  3. ~#8DeepSeek V4.1 FlashEstimated86.4%
  4. #8Gemini 3.1 Pro85.9%
estimated from related benchmarks
GDPval-AA (Elo)
third-party
—
#14/901600Verified
  1. #1Claude Opus 5.51866
  2. #13Qwen3.8 Flash-Next1612
  3. #14DeepSeek V4.1 Flash1600
  4. #15Qwen3.8 2.4T A95B1597
artificialanalysis.ai · 2026-09-24
AutomationBench-AA
third-party
—
#3/8368.9%Verified
  1. #1Muse Wonder Full71.3%
  2. #2Claude Opus 5.569.5%
  3. #3DeepSeek V4.1 Flash68.9%
  4. #4GPT-6 Astra68.5%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
—
~#15/91~40.1%Estimated
  1. #1Muse Spark 1.350.5%
  2. #14GPT-5.6 Terra40.2%
  3. ~#15DeepSeek V4.1 FlashEstimated40.1%
  4. #15DeepSeek V4 Pro (0813)39.6%
estimated from related benchmarks