DeepSeek V4 Flash (Reasoning, High Effort)

April 24, 2026Last synced Aug 1, 2026, 12:18 AM

Human Frontier

89.3

Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.

Blended Price

$0.17/M

Input Price

$0.14/M

Output Price

$0.28/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index

Performance Radar

DeepSeek V4 Flash (Reasoning, High Effort)

Field Average

External Benchmarks

Arena ELO: Coding

How DeepSeek V4 Flash (Reasoning, High Effort) Compares

Axes

X Axis

Y Axis

Bubble Size

Filters

Blended Price (USD)$0.00 – $37.5

AgMoBench Overall≥ 1.8

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu

Show quadrants

anthropic

openai

mistral

azure

cohere

meta

ai21-labs

inclusionai

google

ai2

ibm

alibaba

upstage

nvidia

aws

kimi

nous-research

thinking-machines

minimax

stepfun

tencent

deepseek

zai

multiversecomputing

xiaomi

xai

deepcogito

sarvam

kwaikat

baidu

swiss-ai-initiative

bytedance_seed

inception

reka-ai

arcee

perplexity

Bubble size = Context Window

8191.00

2000000.00

Compare with other models

SWE-rebenchswe_rebench

vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · DeepSeek-V4 Flash [high] · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-V4 Flash [high]__tools · record DeepSeek-V4 Flash [high]__tools:1772323200000:1778803200000

View run source

Source metadata

{
  "passAt5": 57.27272727272727,
  "developer": "deepseek",
  "instanceType": "model",
  "contextPolicy": "128k unless the model supports less",
  "attemptsPerTask": 5,
  "totalTokenUsage": 2996077.38,
  "modelReleaseDate": "2026-04-24",
  "scoreStandardError": 0.9706434774573924,
  "cachedTokenPercentage": 95.49776510326375,
  "modelReleaseTimestamp": 1776988800000,
  "standardContextTokens": 128000,
  "averageInstanceCostUsd": 0.06918754347272726,
  "potentialContamination": true,
  "aggregateTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  },
  "publishedTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  }
}

Evidence observed 2026-05-15

38.4 / 100

SWE-rebenchswe_rebench

vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · DeepSeek-V4 Flash [high] · harness swe-rebench-react@tools · effort high · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider DeepSeek-V4 Flash [high]__tools · record DeepSeek-V4 Flash [high]__tools:1772323200000:1778803200000

View run source

Source metadata

{
  "passAt5": 57.27272727272727,
  "developer": "deepseek",
  "instanceType": "model",
  "contextPolicy": "128k unless the model supports less",
  "attemptsPerTask": 5,
  "totalTokenUsage": 2996077.38,
  "modelReleaseDate": "2026-04-24",
  "scoreStandardError": 0.9706434774573924,
  "cachedTokenPercentage": 95.49776510326375,
  "modelReleaseTimestamp": 1776988800000,
  "standardContextTokens": 128000,
  "averageInstanceCostUsd": 0.06918754347272726,
  "potentialContamination": true,
  "aggregateTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  },
  "publishedTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  }
}

Evidence observed 2026-05-15

38.4 / 100