Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs WizardLM-2 8x22B

Grok 4.20 (Non-Reasoning) has enough public results to be ranked (#54); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

WizardLM-2 8x22B Microsoft

31.4

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 2 categories and WizardLM-2 8x22B in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4.20 (Non-Reasoning) leads 52.8 to 23.3.
  • The biggest single-benchmark swing is GPQA Diamond: 89.3% for Grok 4.20 (Non-Reasoning) and 43.4% for WizardLM-2 8x22B.
  • WizardLM-2 8x22B is cheaper at $0.62 / $0.62 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 66K.
  • WizardLM-2 8x22B has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)WizardLM-2 8x22B
ProviderxAIMicrosoft
Noometry Index48.631.4
Released2026-02-172024-04-15
WeightsProprietaryOpen
Context window1M66K
Max output30K8K
Input $ / M tokens$1.25$0.62
Output $ / M tokens$2.50$0.62
Results tracked462

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

Category by category

Coding Not comparable

Grok 4.20 (Non-Reasoning): 42.1 (#112), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
LMArena WebDev1375—
WeirdML52.3%—
LMArena Coding1459—
ALE-Bench1,150—

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Not comparable

Grok 4.20 (Non-Reasoning): 52.3 (#32), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Chess Puzzles24%—
Thematic Generalization63.8%—
LMArena Hard Prompts1451—
DTBench90.1%—
LMCA38.7%—
Epoch Capabilities Index151.98—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), WizardLM-2 8x22B: 28.9

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
ProofBench14%—
LMArena Math1455—
MATH Level 5—25.7%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), WizardLM-2 8x22B: 23.3

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
GPQA Diamond89.3%43.4%
SimpleQA Verified30.2%—
LMArena Expert1439—

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Not comparable

Grok 4.20 (Non-Reasoning): 54.5 (#40), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
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), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
LMArena Instruction Following1420—

Long Context Not comparable

Grok 4.20 (Non-Reasoning): 45.5 (#34), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
CL-bench22.2%—
CL-bench Life11.9%—
LMArena Longer Query1437—

Writing & Preference Not comparable

Grok 4.20 (Non-Reasoning): 65.7 (#44), WizardLM-2 8x22B: —

BenchmarkGrok 4.20 (Non-Reasoning)WizardLM-2 8x22B
LMArena Text1451—
LMArena Creative Writing1438—
EQ-Bench Creative Writing1574—
LMArena Multi-Turn1456—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than WizardLM-2 8x22B?

Grok 4.20 (Non-Reasoning) has enough public results to be ranked (#54); WizardLM-2 8x22B does not yet, so treat this comparison as directional.

Which is cheaper, Grok 4.20 (Non-Reasoning) or WizardLM-2 8x22B?

WizardLM-2 8x22B is cheaper. It lists at $0.62 per million input tokens and $0.62 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 66K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and WizardLM-2 8x22B share?

1 benchmark has published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and WizardLM-2 8x22B has 2.

Related comparisons

Go deeper