Noometry

Model comparison

DeepSeek V4.1 Flash vs Olmo 3 32b Think

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.7 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Olmo 3 32b Think Allen Institute for AI (Ai2)

38.7

Rank #183 Confirmed

Summary

  • They share 14 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Olmo 3 32b Think in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 36.5.

Side by side

DeepSeek V4.1 FlashOlmo 3 32b Think
ProviderDeepSeekAllen Institute for AI (Ai2)
Noometry Index52.838.7
Released2026-09-09—
WeightsOpenOpen
Context window1M—
Max output393K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.60—
Results tracked3714

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), Olmo 3 32b Think: 38.6 (#172)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Coding15061319
LMArena WebDev1619—
SciCode51.9%—
ALE-Bench1,092—

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), Olmo 3 32b Think: —

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
APEX-Agents39.5%—
GDP.pdf19.8%—

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), Olmo 3 32b Think: 25.9 (#140)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Hard Prompts14831302
NYT Connections (extended)89.6%—
CritPt14.3%—
Mystery Game Puzzles43%—
DTBench89.9%—
LMCA47%—
Surface Evolver Bench46.3%—
Epoch Capabilities Index154.9—

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), Olmo 3 32b Think: 36.5 (#165)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Math14771316
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202598.3%—
ProofBench54%—

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), Olmo 3 32b Think: 35.0 (#190)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Expert15061273
GPQA Diamond89.8%—

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), Olmo 3 32b Think: —

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), Olmo 3 32b Think: 41.2 (#210)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Non-English14481255
LMArena Chinese14971300
LMArena French14521291
LMArena German14841290
LMArena Russian14711254
LMArena Japanese1412—
LMArena Korean1452—
LMArena Spanish1459—

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), Olmo 3 32b Think: 67.2 (#198)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Instruction Following14741275

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), Olmo 3 32b Think: 39.4 (#182)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Longer Query14751296

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), Olmo 3 32b Think: 49.1 (#193)

BenchmarkDeepSeek V4.1 FlashOlmo 3 32b Think
LMArena Text14621300
LMArena Creative Writing14351256
LMArena Multi-Turn14571290
EQ-Bench Creative Writing1540—

Frequently asked questions

Is DeepSeek V4.1 Flash better than Olmo 3 32b Think?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 38.7 on the Noometry Index.

Is DeepSeek V4.1 Flash or Olmo 3 32b Think better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 38.6 in the Noometry coding category.

How many benchmarks do DeepSeek V4.1 Flash and Olmo 3 32b Think share?

14 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper