Noometry

Model comparison

Olmo 3 32b Think vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.7 on the Noometry Index.

Last verified . 14 shared benchmarks.

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

38.7

Rank #183 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Olmo 3 32b Think scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 35.0.

Side by side

Olmo 3 32b ThinkQwen3 235B-A22B
ProviderAllen Institute for AI (Ai2)Alibaba (Qwen)
Noometry Index38.743.5
Released—2025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked1449

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

Category by category

Coding Qwen3 235B-A22B leads

Olmo 3 32b Think: 38.6 (#172), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Coding13191445
Aider Polyglot—59.6%
SciCode—42.4%
WeirdML—41%

Agentic & Tool Use Not comparable

Olmo 3 32b Think: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Olmo 3 32b Think leads

Olmo 3 32b Think: 25.9 (#140), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Hard Prompts13021433
ARC-AGI-2—1.3%
SimpleBench—31%
Kagi LLM Benchmark—69.4%
ARC-AGI-1—11%
CritPt—0%
Chess Puzzles—12%
Mystery Game Puzzles—9%
DTBench—80.3%
LMCA—29.3%
Epoch Capabilities Index—143.85
ForecastBench—59.7

Math Qwen3 235B-A22B leads

Olmo 3 32b Think: 36.5 (#165), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Math13161432
OTIS Mock AIME 2024-2025—86.7%
Omni-MATH—71.8%
MATH Level 5—68.9%
FrontierMath (Feb 2025 set)—8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

Olmo 3 32b Think: 35.0 (#190), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Expert12731463
GPQA Diamond—80.1%
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Confabulations—15.6%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—72.7%

Multilingual Qwen3 235B-A22B leads

Olmo 3 32b Think: 41.2 (#210), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Non-English12551409
LMArena Chinese13001481
LMArena French12911445
LMArena German12901433
LMArena Russian12541411
LMArena Japanese—1399
LMArena Korean—1391
LMArena Spanish—1430

Instruction Following Qwen3 235B-A22B leads

Olmo 3 32b Think: 67.2 (#198), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Instruction Following12751408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Olmo 3 32b Think: 39.4 (#182), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Longer Query12961426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

Olmo 3 32b Think: 49.1 (#193), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkOlmo 3 32b ThinkQwen3 235B-A22B
LMArena Text13001419
LMArena Creative Writing12561384
LMArena Multi-Turn12901432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Olmo 3 32b Think better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.7 on the Noometry Index.

Is Olmo 3 32b Think or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 38.6 in the Noometry coding category.

How many benchmarks do Olmo 3 32b Think and Qwen3 235B-A22B share?

14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper