Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Qwen3-30B-A3B

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 7.3× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Qwen3-30B-A3B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 22.2.
  • The biggest single-benchmark swing is WeirdML: 52.3% for Grok 4.20 (Non-Reasoning) and 29.8% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 41K.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Qwen3-30B-A3B
ProviderxAIAlibaba (Qwen)
Noometry Index48.638.9
Released2026-02-172025-04-28
WeightsProprietaryOpen
Context window1M41K
Max output30K16K
Input $ / M tokens$1.25$0.12
Output $ / M tokens$2.50$0.50
Results tracked4632

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
WeirdML52.3%29.8%
LMArena Coding14591416
LMArena WebDev1375—
SciCode—33.3%
ALE-Bench1,150—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen3-30B-A3B: 29.8 (#82)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
Terminal-Bench57.3%—
Berkeley Function Calling Leaderboard—41.4%
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
Kagi LLM Benchmark75%54.9%
Chess Puzzles24%8%
LMArena Hard Prompts14511398
DTBench90.1%69.3%
LMCA38.7%22.4%
Epoch Capabilities Index151.98139.63
ARC-AGI-265.1%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
CritPt—0.3%
Thematic Generalization63.8%—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
OTIS Mock AIME 2024-202592.2%70.3%
LMArena Math14551394
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions—47.8%
ProofBench14%—

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
GPQA Diamond89.3%70.1%
LMArena Expert14391396
SimpleQA Verified30.2%—
Confabulations—12.3%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen3-30B-A3B: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen3-30B-A3B: 49.5 (#132)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
LMArena Non-English14411372
LMArena Chinese14811433
LMArena French14761418
LMArena German14651380
LMArena Japanese14491337
LMArena Korean14171331
LMArena Russian14581370
LMArena Spanish14431404

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen3-30B-A3B: 72.0 (#142)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
LMArena Instruction Following14201363

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
LMArena Longer Query14371379
Fiction.LiveBench—40.6%
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen3-30B-A3B: 55.6 (#143)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3-30B-A3B
LMArena Text14511384
LMArena Creative Writing14381317
LMArena Multi-Turn14561378
Short-Story Creative Writing—75.3%
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Qwen3-30B-A3B?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 7.3× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Qwen3-30B-A3B better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 41K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen3-30B-A3B share?

25 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper