Noometry

Model comparison

DeepSeek V4 Flash vs o1-mini

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 34.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

o1-mini OpenAI

34.0

Rank #235 Confirmed

Summary

  • They share 24 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and o1-mini in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 8.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 89% for DeepSeek V4 Flash and 14% for o1-mini.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 Flasho1-mini
ProviderDeepSeekOpenAI
Noometry Index53.634.0
Released2026-04-242024-09-12
WeightsOpenProprietary
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked4139

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), o1-mini: 35.5 (#224)

BenchmarkDeepSeek V4 Flasho1-mini
WeirdML63%36.3%
LMArena Coding14571362
FrontierCode18.8%—
Aider Polyglot—32.9%
LMArena WebDev1582—
SciCode49.9%—
LiveBench Coding—48%
ALE-Bench1,306—
HumanEval+—89%
MBPP+—78.8%

Agentic & Tool Use Not comparable

DeepSeek V4 Flash: —, o1-mini: 24.6 (#118)

BenchmarkDeepSeek V4 Flasho1-mini
Cybench—10%

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), o1-mini: 8.8 (#346)

BenchmarkDeepSeek V4 Flasho1-mini
ARC-AGI-261.4%0.8%
SimpleBench61.1%18.1%
ARC-AGI-189%14%
LMArena Hard Prompts14441333
Epoch Capabilities Index154.49135.82
Kagi LLM Benchmark52.2%—
NYT Connections (extended)89.6%—
CritPt16.6%—
Chess Puzzles33%—
LiveBench Reasoning—72.3%
Mystery Game Puzzles34%—
DTBench90.9%—
LiveBench Data Analysis—57.9%
LMCA41.7%—
LiveBench—57.8%

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), o1-mini: 35.4 (#186)

BenchmarkDeepSeek V4 Flasho1-mini
OTIS Mock AIME 2024-202594.4%46.9%
LMArena Math14271358
FrontierMath (Tiers 1-3)57.5%—
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
ProofBench56%—
LiveBench Math—62%
MATH Level 5—89.2%
FrontierMath (Feb 2025 set)—1.7%

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), o1-mini: 34.9 (#192)

BenchmarkDeepSeek V4 Flasho1-mini
GPQA Diamond91%62.4%
LMArena Expert14411316
SimpleQA Verified33.6%—
Confabulations—18.6%

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), o1-mini: 43.6 (#182)

BenchmarkDeepSeek V4 Flasho1-mini
LMArena Non-English14201289
LMArena Chinese14681314
LMArena French14391293
LMArena German14181278
LMArena Japanese14061245
LMArena Korean13841223
LMArena Russian14281283
LMArena Spanish14361303

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 74.9 (#81), o1-mini: 66.7 (#206)

BenchmarkDeepSeek V4 Flasho1-mini
LMArena Instruction Following14211304
LiveBench Instruction Following—65.4%

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#85), o1-mini: 40.1 (#161)

BenchmarkDeepSeek V4 Flasho1-mini
LMArena Longer Query14341320

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), o1-mini: 48.4 (#202)

BenchmarkDeepSeek V4 Flasho1-mini
LMArena Text14321317
LMArena Creative Writing14031244
LMArena Multi-Turn14491314
Short-Story Creative Writing—64.9%
EQ-Bench Creative Writing1559—
LiveBench Language—40.9%

Frequently asked questions

Is DeepSeek V4 Flash better than o1-mini?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 34.0 on the Noometry Index.

Is DeepSeek V4 Flash or o1-mini better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 35.5 in the Noometry coding category.

How many benchmarks do DeepSeek V4 Flash and o1-mini share?

24 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and o1-mini has 39.

Related comparisons

Go deeper