Noometry

Model comparison

DeepSeek V4 Flash vs Solar Pro4

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 42.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Summary

  • They share 18 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Solar Pro4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 28.5.
  • DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
  • DeepSeek V4 Flash accepts more context: 1M tokens versus 524K.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 FlashSolar Pro4
ProviderDeepSeekUpstage
Noometry Index53.642.1
Released2026-04-242026-08-06
WeightsOpenProprietary
Context window1M524K
Max output393K131K
Input $ / M tokens$0.15$0.30
Output $ / M tokens$0.60$1.20
Results tracked4118

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), Solar Pro4: 40.1 (#149)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena WebDev15821371
LMArena Coding14571437
FrontierCode18.8%—
SciCode49.9%—
WeirdML63%—
ALE-Bench1,306—

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), Solar Pro4: 28.5 (#104)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Hard Prompts14441399
ARC-AGI-261.4%—
SimpleBench61.1%—
Kagi LLM Benchmark52.2%—
NYT Connections (extended)89.6%—
ARC-AGI-189%—
CritPt16.6%—
Chess Puzzles33%—
Mystery Game Puzzles34%—
DTBench90.9%—
LMCA41.7%—
Epoch Capabilities Index154.49—

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), Solar Pro4: 38.8 (#128)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Math14271416
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench56%—

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), Solar Pro4: 39.8 (#129)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Expert14411427
GPQA Diamond91%—
SimpleQA Verified33.6%—

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), Solar Pro4: 48.7 (#139)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Non-English14201361
LMArena Chinese14681415
LMArena French14391397
LMArena German14181364
LMArena Japanese14061309
LMArena Korean13841382
LMArena Russian14281360
LMArena Spanish14361401

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 74.9 (#81), Solar Pro4: 72.7 (#132)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Instruction Following14211377

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#85), Solar Pro4: 42.1 (#130)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Longer Query14341381

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), Solar Pro4: 56.5 (#138)

BenchmarkDeepSeek V4 FlashSolar Pro4
LMArena Text14321386
LMArena Creative Writing14031316
LMArena Multi-Turn14491385
EQ-Bench Creative Writing1559—

Frequently asked questions

Is DeepSeek V4 Flash better than Solar Pro4?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 42.1 on the Noometry Index.

Which is cheaper, DeepSeek V4 Flash or Solar Pro4?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.

Is DeepSeek V4 Flash or Solar Pro4 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4 Flash does, with 1M tokens against 524K.

How many benchmarks do DeepSeek V4 Flash and Solar Pro4 share?

18 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Solar Pro4 has 18.

Related comparisons

Go deeper