Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Hy4 preview

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 45.3 on the Noometry Index.

Last verified . 3 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Hy4 preview Tencent

45.3

Rank #73 Reported

Summary

  • They share 3 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 1 category and Hy4 preview in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 31.9.
  • The biggest single-benchmark swing is ProofBench: 14% for Grok 4.20 (Non-Reasoning) and 75% for Hy4 preview.
  • Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Hy4 preview accepts more context: 1.05M tokens versus 1M.
  • Hy4 preview has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Hy4 preview
ProviderxAITencent
Noometry Index48.645.3
Released2026-02-172026-08-28
WeightsProprietaryOpen
Context window1M1.05M
Max output30K64K
Input $ / M tokens$1.25$0.75
Output $ / M tokens$2.50$2.25
Results tracked463

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

Category by category

Coding Hy4 preview leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Hy4 preview: 51.6 (#38)

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
LMArena WebDev13751632
WeirdML52.3%—
LMArena Coding1459—
ALE-Bench1,150—

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Hy4 preview: 31.9 (#79)

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
NYT Connections (extended)85.4%68.2%
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
ARC-AGI-189.5%—
Chess Puzzles24%—
Thematic Generalization63.8%—
LMArena Hard Prompts1451—
DTBench90.1%—
LMCA38.7%—
Epoch Capabilities Index151.98—
ForecastBench61.4—

Math Hy4 preview leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Hy4 preview: 55.7 (#42)

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
ProofBench14%75%
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
LMArena Math1455—

Knowledge Not comparable

Grok 4.20 (Non-Reasoning): 52.8 (#60), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
GPQA Diamond89.3%—
SimpleQA Verified30.2%—
LMArena Expert1439—

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Not comparable

Grok 4.20 (Non-Reasoning): 54.5 (#40), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
LMArena Non-English1441—
LMArena Chinese1481—
LMArena French1476—
LMArena German1465—
LMArena Japanese1449—
LMArena Korean1417—
LMArena Russian1458—
LMArena Spanish1443—

Instruction Following Not comparable

Grok 4.20 (Non-Reasoning): 74.8 (#83), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
LMArena Instruction Following1420—

Long Context Not comparable

Grok 4.20 (Non-Reasoning): 45.5 (#34), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
CL-bench22.2%—
CL-bench Life11.9%—
LMArena Longer Query1437—

Writing & Preference Not comparable

Grok 4.20 (Non-Reasoning): 65.7 (#44), Hy4 preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Hy4 preview
LMArena Text1451—
LMArena Creative Writing1438—
EQ-Bench Creative Writing1574—
LMArena Multi-Turn1456—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Hy4 preview?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 45.3 on the Noometry Index.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Hy4 preview?

Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Hy4 preview better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.1 in the Noometry coding category.

Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 1M.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Hy4 preview share?

3 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Hy4 preview has 3.

Related comparisons

Go deeper