Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Qwen3 Max

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 43.7 on the Noometry Index.

Last verified . 30 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 7 categories and Qwen3 Max in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 22.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 85.4% for Grok 4.20 (Non-Reasoning) and 30.1% for Qwen3 Max.
  • Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 262K.

Side by side

Grok 4.20 (Non-Reasoning)Qwen3 Max
ProviderxAIAlibaba (Qwen)
Noometry Index48.643.7
Released2026-02-172025-09-23
WeightsProprietaryProprietary
Context window1M262K
Max output30K66K
Input $ / M tokens$1.25$1.20
Output $ / M tokens$2.50$6
Results tracked4633

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

Category by category

Coding Too close to call

Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen3 Max: 43.0 (#93)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
LMArena Coding14591456
ALE-Bench1,150370.45
LMArena WebDev1375—
WeirdML52.3%—

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen3 Max: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
Vending-Bench 24,66371.56
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen3 Max: 22.6 (#190)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
Kagi LLM Benchmark75%72.5%
NYT Connections (extended)85.4%30.1%
Chess Puzzles24%4%
LMArena Hard Prompts14511448
DTBench90.1%82.1%
LMCA38.7%28.3%
Epoch Capabilities Index151.98142.38
ARC-AGI-265.1%—
ARC-AGI-189.5%—
Thematic Generalization63.8%—
Mystery Game Puzzles—5%
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen3 Max: 38.7 (#131)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
FrontierMath (Tiers 1-3)44.9%18.9%
OTIS Mock AIME 2024-202592.2%73.3%
LMArena Math14551446
FrontierMath Tier 417.1%—
ProofBench14%—
MATH Level 5—97.1%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen3 Max: 48.1 (#78)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
GPQA Diamond89.3%72.6%
SimpleQA Verified30.2%48.7%
LMArena Expert14391455

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen3 Max: —

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

Multilingual Too close to call

Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen3 Max: 53.7 (#62)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
LMArena Non-English14411429
LMArena Chinese14811478
LMArena French14761449
LMArena German14651463
LMArena Japanese14491397
LMArena Korean14171399
LMArena Russian14581428
LMArena Spanish14431462

Instruction Following Too close to call

Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen3 Max: 74.8 (#87)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
LMArena Instruction Following14201419

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen3 Max: 41.6 (#134)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
CL-bench22.2%14.5%
LMArena Longer Query14371438
Fiction.LiveBench—66.7%
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen3 Max: 62.4 (#76)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen3 Max
LMArena Text14511439
LMArena Creative Writing14381402
LMArena Multi-Turn14561446
EQ-Bench Creative Writing1574—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Qwen3 Max?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 43.7 on the Noometry Index.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Qwen3 Max?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is Grok 4.20 (Non-Reasoning) or Qwen3 Max better for coding?

They score almost the same on coding (42.1 vs 43.0); test both on your own repository before choosing.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 262K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen3 Max share?

30 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper