Noometry

Model comparison

Granite 4.2 30b vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.8 on the Noometry Index.

Last verified . 11 shared benchmarks.

Granite 4.2 30b IBM

41.8

Rank #130 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 1 category and Qwen3 235B-A22B in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Granite 4.2 30b leads 27.8 to 15.7.

Side by side

Granite 4.2 30bQwen3 235B-A22B
ProviderIBMAlibaba (Qwen)
Noometry Index41.843.5
Released—2025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked1149

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

Category by category

Coding Qwen3 235B-A22B leads

Granite 4.2 30b: 41.0 (#126), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Coding13961445
Aider Polyglot—59.6%
SciCode—42.4%
WeirdML—41%

Agentic & Tool Use Not comparable

Granite 4.2 30b: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Granite 4.2 30b leads

Granite 4.2 30b: 27.8 (#112), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Hard Prompts13741433
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 Not comparable

Granite 4.2 30b: —, Qwen3 235B-A22B: 50.4 (#57)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
OTIS Mock AIME 2024-2025—86.7%
Omni-MATH—71.8%
LMArena Math—1432
MATH Level 5—68.9%
FrontierMath (Feb 2025 set)—8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

Granite 4.2 30b: 39.1 (#138), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Expert14061463
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

Granite 4.2 30b: 47.3 (#151), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Non-English13401409
LMArena Chinese14141481
LMArena Russian13431411
LMArena French—1445
LMArena German—1433
LMArena Japanese—1399
LMArena Korean—1391
LMArena Spanish—1430

Instruction Following Qwen3 235B-A22B leads

Granite 4.2 30b: 71.2 (#155), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Instruction Following13471408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Granite 4.2 30b: 41.4 (#140), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Longer Query13591426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

Granite 4.2 30b: 53.8 (#156), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkGranite 4.2 30bQwen3 235B-A22B
LMArena Text13611419
LMArena Creative Writing12881384
LMArena Multi-Turn13391432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Granite 4.2 30b better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 41.8 on the Noometry Index.

Is Granite 4.2 30b or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 41.0 in the Noometry coding category.

How many benchmarks do Granite 4.2 30b and Qwen3 235B-A22B share?

11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper