Noometry

Model comparison

Deepseek Coder v2 vs DeepSeek V4 Flash

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and DeepSeek V4 Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 23.6.

Side by side

Deepseek Coder v2DeepSeek V4 Flash
ProviderDeepSeekDeepSeek
Noometry Index35.953.6
Released2024-06-172026-04-24
WeightsOpenOpen
Context window—1M
Max output—393K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.60
Results tracked2441

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding DeepSeek V4 Flash leads

Deepseek Coder v2: 38.1 (#183), DeepSeek V4 Flash: 47.9 (#59)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Coding12511457
FrontierCode—18.8%
LMArena WebDev—1582
SciCode—49.9%
WeirdML—63%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
ALE-Bench—1,306
HumanEval+82.3%—
MBPP+75.1%—

Reasoning DeepSeek V4 Flash leads

Deepseek Coder v2: 23.6 (#176), DeepSeek V4 Flash: 53.7 (#30)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Hard Prompts12071444
ARC-AGI-2—61.4%
SimpleBench—61.1%
Kagi LLM Benchmark—52.2%
NYT Connections (extended)—89.6%
ARC-AGI-1—89%
CritPt—16.6%
Chess Puzzles—33%
Mystery Game Puzzles—34%
DTBench—90.9%
LMCA—41.7%
Epoch Capabilities Index—154.49
WinoGrande83.7%—

Math DeepSeek V4 Flash leads

Deepseek Coder v2: 34.9 (#190), DeepSeek V4 Flash: 60.3 (#37)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Math12411427
FrontierMath (Tiers 1-3)—57.5%
FrontierMath Tier 4—24.4%
MathArena Final-Answer Competitions—76.5%
OTIS Mock AIME 2024-2025—94.4%
ProofBench—56%
GSM8K94.5%—

Knowledge DeepSeek V4 Flash leads

Deepseek Coder v2: 32.3 (#212), DeepSeek V4 Flash: 55.4 (#48)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Expert11811441
GPQA Diamond—91%
SimpleQA Verified—33.6%
ARC (AI2) Challenge64.3%—

Multilingual DeepSeek V4 Flash leads

Deepseek Coder v2: 36.3 (#240), DeepSeek V4 Flash: 53.0 (#72)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Non-English11821420
LMArena Chinese12011468
LMArena French11851439
LMArena German11641418
LMArena Japanese11261406
LMArena Korean11041384
LMArena Russian11881428
LMArena Spanish11531436

Instruction Following DeepSeek V4 Flash leads

Deepseek Coder v2: 61.7 (#242), DeepSeek V4 Flash: 74.9 (#81)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Instruction Following11801421

Long Context DeepSeek V4 Flash leads

Deepseek Coder v2: 37.0 (#224), DeepSeek V4 Flash: 43.8 (#85)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Longer Query12191434

Writing & Preference DeepSeek V4 Flash leads

Deepseek Coder v2: 38.2 (#253), DeepSeek V4 Flash: 63.8 (#61)

BenchmarkDeepseek Coder v2DeepSeek V4 Flash
LMArena Text11911432
LMArena Creative Writing11201403
LMArena Multi-Turn11771449
EQ-Bench Creative Writing—1559

Frequently asked questions

Is Deepseek Coder v2 better than DeepSeek V4 Flash?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or DeepSeek V4 Flash better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and DeepSeek V4 Flash share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek V4 Flash has 41.

Related comparisons

Go deeper