Skip to content
Model Pareto

DeepSeek V4.1 Flash NVFP4

NVIDIAOpen weightsNVFP4quantized from DeepSeek V4.1 Flashhuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~160tok/sest.
Context
1Mtokens

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
4× B200 180GB
NVFP4 weights
Throughput
~17,975 tok/s
many requests batched
Price
$0.15–1.32 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (NVFP4, ~93 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • NVFP4 weights (552B params, 16B active per token) + 40% KV-cache headroom ≈ 435 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~17,975 output tok/s aggregate at batch 514 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~265,781 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~86.6%
  1. #1Claude Opus 596.0%
  2. ~#2DeepSeek V4.1 Flash NVFP4Estimated86.6%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#19 of 32 (estimated)~64.2%
  1. #1GPT-6.1 Sol75.2%
  2. #2DeepSeek V4.1 Flash74.2%
  3. #17Hy4 preview64.3%
  4. ~#19DeepSeek V4.1 Flash NVFP4Estimated64.2%
  5. #19GPT-6 Luna63.7%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#9 of 15 (estimated)~53.0
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #8GLM-5.353.6
  4. ~#9DeepSeek V4.1 Flash NVFP4Estimated53.0
  5. #9Kimi K351.9
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#2 of 5 (estimated)~89.8%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2DeepSeek V4.1 Flash NVFP4Estimated89.8%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#16 of 54 (estimated)~1455 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #15GPT-5.6 Terra1456
  4. ~#16DeepSeek V4.1 Flash NVFP4Estimated1455
  5. #16DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#16 of 54 (estimated)~1466 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #15GPT-5.6 Terra1466
  4. ~#16DeepSeek V4.1 Flash NVFP4Estimated1466
  5. #16DeepSeek V4 Pro (0813)1463
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2DeepSeek V4.1 Flash NVFP4Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~80.4%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5DeepSeek V4.1 Flash NVFP4Estimated80.4%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~86.8%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4DeepSeek V4.1 Flash NVFP4Estimated86.8%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#17 of 43 (estimated)~16.9%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #16Grok 4.617.2%
  4. ~#17DeepSeek V4.1 Flash NVFP4Estimated16.9%
  5. #17Qwen3.8 27B16.6%
No published score — estimated from related benchmarks
ChartographyEstimated
~#11 of 23 (estimated)~27.4%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #10Muse Spark 1.327.6%
  4. ~#11DeepSeek V4.1 Flash NVFP4Estimated27.4%
  5. #11Claude Opus 527.3%
No published score — estimated from related benchmarks

Hard reasoning

Humanity's Last ExamEstimated
~#44 of 182 (estimated)~31.4%
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #43Inkling31.9%
  4. ~#44DeepSeek V4.1 Flash NVFP4Estimated31.4%
  5. #44A.X-K229.6%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 30 (estimated)~98.9%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2DeepSeek V4.1 Flash NVFP4Estimated98.9%
  3. #2Inkling97.1%
No published score — estimated from related benchmarks