Noometry

Model comparison

DeepSeek-V3.2-Exp vs Olmo 3 32b Think

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 38.7 on the Noometry Index.

Last verified . 14 shared benchmarks.

DeepSeek-V3.2-Exp DeepSeek

44.3

Rank #78 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-V3.2-Exp scores higher in 7 categories and Olmo 3 32b Think in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 35.0.

Side by side

DeepSeek-V3.2-ExpOlmo 3 32b Think
ProviderDeepSeekAllen Institute for AI (Ai2)
Noometry Index44.338.7
Released2025-09-29—
WeightsOpenOpen
Context window164K—
Max output66K—
Input $ / M tokens$0.26—
Output $ / M tokens$0.38—
Results tracked4914

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

Category by category

Coding DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 46.5 (#65), Olmo 3 32b Think: 38.6 (#172)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Coding14541319
SWE-bench Verified (bash only)70%—
Aider Polyglot74.2%—
LMArena WebDev1362—
SWE-bench Multilingual59%—
SciCode38.9%—
WeirdML39.5%—

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 32.7 (#59), Olmo 3 32b Think: —

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
Terminal-Bench39.6%—
APEX-Agents21.3%—
Berkeley Function Calling Leaderboard56.7%—
TheAgentCompany42.9%—
Vending-Bench 21,034—

Reasoning Olmo 3 32b Think leads

DeepSeek-V3.2-Exp: 22.1 (#208), Olmo 3 32b Think: 25.9 (#140)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Hard Prompts14341302
ARC-AGI-24%—
Kagi LLM Benchmark52.2%—
NYT Connections (extended)36.7%—
ARC-AGI-157%—
CritPt2.9%—
Chess Puzzles14%—
Thematic Generalization65%—
DTBench87.7%—
LMCA29.1%—
Epoch Capabilities Index146.27—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 41.7 (#87), Olmo 3 32b Think: 36.5 (#165)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Math14351316
MathArena Final-Answer Competitions57.7%—
OTIS Mock AIME 2024-202587.8%—
ProofBench8%—
FrontierMath (Feb 2025 set)22.1%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.7 (#66), Olmo 3 32b Think: 35.0 (#190)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Expert14361273
GPQA Diamond83.4%—
Vectara Hallucination Rate5.3%—

Multilingual DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 52.2 (#90), Olmo 3 32b Think: 41.2 (#210)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Non-English14091255
LMArena Chinese14611300
LMArena French14331291
LMArena German14401290
LMArena Russian14241254
LMArena Japanese1374—
LMArena Korean1371—
LMArena Spanish1440—

Instruction Following DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 74.5 (#93), Olmo 3 32b Think: 67.2 (#198)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Instruction Following14131275

Long Context DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 47.6 (#16), Olmo 3 32b Think: 39.4 (#182)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Longer Query14281296
Fiction.LiveBench83.3%—
CL-bench13.2%—
CL-bench Life9.5%—

Writing & Preference DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 62.4 (#77), Olmo 3 32b Think: 49.1 (#193)

BenchmarkDeepSeek-V3.2-ExpOlmo 3 32b Think
LMArena Text14251300
LMArena Creative Writing14031256
LMArena Multi-Turn14271290
EQ-Bench Creative Writing1515—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than Olmo 3 32b Think?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 38.7 on the Noometry Index.

Is DeepSeek-V3.2-Exp or Olmo 3 32b Think better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 38.6 in the Noometry coding category.

How many benchmarks do DeepSeek-V3.2-Exp and Olmo 3 32b Think share?

14 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper