Noometry

Model comparison

Olmo 3 32b Think vs Qwen3-4B

Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 31.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

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

38.1

Rank #182 Confirmed

Qwen3-4B Alibaba (Qwen)

31.5

Rank #261 Confirmed

Summary

  • The widest gap is in reasoning, where Olmo 3 32b Think leads 24.9 to 18.5.

Side by side

Olmo 3 32b ThinkQwen3-4B
ProviderAllen Institute for AI (Ai2)Alibaba (Qwen)
Noometry Index38.131.5
Released—2025-04-29
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked146

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

Category by category

Coding Not comparable

Olmo 3 32b Think: 38.0 (#169), Qwen3-4B: —

BenchmarkOlmo 3 32b ThinkQwen3-4B
LMArena Coding1318—

Agentic & Tool Use Not comparable

Olmo 3 32b Think: —, Qwen3-4B: 27.3 (#94)

BenchmarkOlmo 3 32b ThinkQwen3-4B
Berkeley Function Calling Leaderboard—35.7%

Reasoning Olmo 3 32b Think leads

Olmo 3 32b Think: 24.9 (#138), Qwen3-4B: 18.5 (#264)

BenchmarkOlmo 3 32b ThinkQwen3-4B
Chess Puzzles—4%
LMArena Hard Prompts1302—

Math Olmo 3 32b Think leads

Olmo 3 32b Think: 33.8 (#165), Qwen3-4B: 28.5 (#228)

BenchmarkOlmo 3 32b ThinkQwen3-4B
MathArena Final-Answer Competitions—38.5%
OTIS Mock AIME 2024-2025—52.2%
LMArena Math1315—

Knowledge Olmo 3 32b Think leads

Olmo 3 32b Think: 34.4 (#189), Qwen3-4B: 33.0 (#198)

BenchmarkOlmo 3 32b ThinkQwen3-4B
GPQA Diamond—52.3%
Vectara Hallucination Rate—5.7%
LMArena Expert1272—

Multilingual Not comparable

Olmo 3 32b Think: 41.4 (#205), Qwen3-4B: —

BenchmarkOlmo 3 32b ThinkQwen3-4B
LMArena Non-English1255—
LMArena Chinese1300—
LMArena French1291—
LMArena German1290—
LMArena Russian1255—

Instruction Following Not comparable

Olmo 3 32b Think: 67.4 (#193), Qwen3-4B: —

BenchmarkOlmo 3 32b ThinkQwen3-4B
LMArena Instruction Following1275—

Long Context Not comparable

Olmo 3 32b Think: 39.4 (#177), Qwen3-4B: —

BenchmarkOlmo 3 32b ThinkQwen3-4B
LMArena Longer Query1296—

Writing & Preference Not comparable

Olmo 3 32b Think: 49.2 (#188), Qwen3-4B: —

BenchmarkOlmo 3 32b ThinkQwen3-4B
LMArena Text1300—
LMArena Creative Writing1256—
LMArena Multi-Turn1289—

Frequently asked questions

Is Olmo 3 32b Think better than Qwen3-4B?

Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 31.5 on the Noometry Index.

How many benchmarks do Olmo 3 32b Think and Qwen3-4B share?

0 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper