Enter opens the highlighted result. Esc closes.

DeepSeek V4 Flash 0423 vs Qwen2.5 72B Instruct

DeepSeek V4 Flash 0423 leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 24.4 to 7.7, and DeepSeek V4 Flash 0423 costs 1.4x less per output token ($0.28 vs $0.40 per million). Updated October 21, 2026; 32 benchmarks have a result for both.

Replace DeepSeek V4 Flash 0423 Replace Qwen2.5 72B Instruct
DeepSeek V4 Flash 0423DeepSeek
Coding
No data
Overall
No data
Output $/M
$0.28
32
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
vs boards won of 32 shared

DeepSeek V4 Flash 0423 or Qwen2.5 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V4 Flash 0423 for output tokens 1.4x cheaper ($0.28 vs $0.40 per million) and a larger context window (1.05M against 33K tokens).

Model ADeepSeek V4 Flash 0423DeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
32
DeepSeek V4 Flash 0423 only
17
Qwen2.5 72B Instruct only
21
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V4 Flash 0423 not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Reasoning, 29.9 points apart on average over 3 shared benchmarks.
Widest single gap
LMArena Text: Japanese: DeepSeek V4 Flash 0423 1389 against Qwen2.5 72B Instruct 1180, 34.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Flash 0423 $0.28 against Qwen2.5 72B Instruct $0.40 per million output tokens, 1.4x apart.
Context window
DeepSeek V4 Flash 0423 takes 1.05M tokens, Qwen2.5 72B Instruct 33K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V4 Flash 0423BarsQwen2.5 72B InstructTies
Coding30
Intelligence20
Reasoning30
Math20
Knowledge40
General180
All shared boards320
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
LMArena WebDev1582Not measuredOnly DeepSeek V4 Flash 0423 measured
AA Coding Index52.0Not measuredOnly DeepSeek V4 Flash 0423 measured
LiveCodeBench (Artificial Analysis run)Not measured27.6%Only Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)Not measured4.5%Only Qwen2.5 72B Instruct measured
WeirdML45.6%16.0%DeepSeek V4 Flash 0423
ALE-Bench678.2Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: coding14571292DeepSeek V4 Flash 0423
LMArena Text: software and IT14531292DeepSeek V4 Flash 0423
LMArena WebDev: React1585Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena WebDev: HTML1558Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
AA Intelligence Index24.47.7DeepSeek V4 Flash 0423
Epoch Capabilities Index146.1129.0DeepSeek V4 Flash 0423
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Agentic work benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Flash 0423 measured
τ²-Bench TelecomNot measured34.5%Only Qwen2.5 72B Instruct measured
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)Not measured49.1%Only Qwen2.5 72B Instruct measured
Humanity's Last Exam (Artificial Analysis run)Not measured3.6%Only Qwen2.5 72B Instruct measured
GPQA Diamond (Epoch AI run)Not measured49.1%Only Qwen2.5 72B Instruct measured
SimpleBench46.3%Not measuredOnly DeepSeek V4 Flash 0423 measured
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts14441271DeepSeek V4 Flash 0423
LMArena Text: expert14411245DeepSeek V4 Flash 0423
LMArena Text: hard prompts in English14491279DeepSeek V4 Flash 0423
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
AA Math IndexNot measured14.0Only Qwen2.5 72B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured14.0%Only Qwen2.5 72B Instruct measured
OTIS Mock AIMENot measured8.1%Only Qwen2.5 72B Instruct measured
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math14261283DeepSeek V4 Flash 0423
LMArena Text: mathematical work14321290DeepSeek V4 Flash 0423
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)Not measured72.0%Only Qwen2.5 72B Instruct measured
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science14461275DeepSeek V4 Flash 0423
LMArena Text: medicine and healthcare14481258DeepSeek V4 Flash 0423
LMArena Text: legal and government14391288DeepSeek V4 Flash 0423
LMArena Text: business and finance14251253DeepSeek V4 Flash 0423
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
Design Arena: websites1208Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: UI components1165Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: game dev1197Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: data viz1127Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: 3D1189Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: all code categories1205Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: SVG1155Not measuredOnly DeepSeek V4 Flash 0423 measured
Design Arena: ASCII art1109Not measuredOnly DeepSeek V4 Flash 0423 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
General benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
IFBenchNot measured36.9%Only Qwen2.5 72B Instruct measured
DTBench86.4%62.9%DeepSeek V4 Flash 0423
LMCA35.9%13.4%DeepSeek V4 Flash 0423
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text14321269DeepSeek V4 Flash 0423
LMArena Text: instruction following14211254DeepSeek V4 Flash 0423
LMArena Text: creative writing14031221DeepSeek V4 Flash 0423
LMArena Text: English14411283DeepSeek V4 Flash 0423
LMArena Text: non-English14191252DeepSeek V4 Flash 0423
LMArena Text: Chinese14631273DeepSeek V4 Flash 0423
LMArena Text: German14191234DeepSeek V4 Flash 0423
LMArena Text: Japanese13891180DeepSeek V4 Flash 0423
LMArena Text: Korean13831188DeepSeek V4 Flash 0423
LMArena Text: French14391280DeepSeek V4 Flash 0423
LMArena Text: Spanish14361255DeepSeek V4 Flash 0423
LMArena Text: Russian14271264DeepSeek V4 Flash 0423
LMArena Text: Polish1436Not measuredOnly DeepSeek V4 Flash 0423 measured
LMArena Text: multi-turn14491272DeepSeek V4 Flash 0423
LMArena Text: longer queries14341281DeepSeek V4 Flash 0423
LMArena Text: writing and language14101247DeepSeek V4 Flash 0423
LMArena Text: entertainment and media14001211DeepSeek V4 Flash 0423
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
BenchmarkDeepSeek V4 Flash 0423Qwen2.5 72B InstructLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V4 Flash 0423$0.0003Fits in one request
Qwen2.5 72B Instruct$0.0006Fits in one request

DeepSeek V4 Flash 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Flash 0423$0.0073Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

DeepSeek V4 Flash 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Flash 0423$0.029Fits in one request
Qwen2.5 72B Instruct$0.076Exceeds the context window

DeepSeek V4 Flash 0423 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V4 Flash 0423 and Qwen2.5 72B Instruct
SpecificationDeepSeek V4 Flash 0423Qwen2.5 72B Instruct
MakerDeepSeekQwen
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026September 19, 2024
Context window1.05M33K
Input $/Mtok$0.13$0.36
Output $/Mtok$0.28$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Flash 0423 better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 1.4x cheaper ($0.28 vs $0.40 per million) and a larger context window (1.05M against 33K tokens).

Which is cheaper, DeepSeek V4 Flash 0423 or Qwen2.5 72B Instruct?

DeepSeek V4 Flash 0423 costs $0.13 per million input tokens and $0.28 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V4 Flash 0423 or Qwen2.5 72B Instruct?

DeepSeek V4 Flash 0423, with 1.05M tokens against 33K.

How many benchmarks is the DeepSeek V4 Flash 0423 vs Qwen2.5 72B Instruct comparison based on?

32 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next