Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Nova 2.0 Pro Preview

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 32.8 on the Noometry Index.

Last verified . 0 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.5

Rank #48 Confirmed

Nova 2.0 Pro Preview Amazon

32.8

Rank #241 Reported

Summary

  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 21.7.

Side by side

Grok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
ProviderxAIAmazon
Noometry Index48.532.8
Released2026-02-172025-12-02
WeightsProprietaryProprietary
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked463

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): 41.8 (#104), Nova 2.0 Pro Preview: 40.2 (#130)

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
LMArena WebDev1374—
SciCode—42.7%
WeirdML52.3%—
LMArena Coding1458—
ALE-Bench1,150—

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

Grok 4.20 (Non-Reasoning): 34.3 (#43), Nova 2.0 Pro Preview: 21.9 (#127)

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
Terminal-Bench57.3%—
τ²-bench Banking18%—
GDP.pdf—2%
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.2 (#30), Nova 2.0 Pro Preview: 21.7 (#189)

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
CritPt—0%
Chess Puzzles24%—
Thematic Generalization63.8%—
LMArena Hard Prompts1451—
DTBench90.1%—
LMCA38.7%—
Epoch Capabilities Index152.01—
ForecastBench61.4—

Math Not comparable

Grok 4.20 (Non-Reasoning): 48.0 (#54), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202592.2%—
ProofBench14%—
LMArena Math1455—

Knowledge Not comparable

Grok 4.20 (Non-Reasoning): 52.8 (#54), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
GPQA Diamond89.3%—
SimpleQA Verified30.2%—
LMArena Expert1440—

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.2 (#88), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Not comparable

Grok 4.20 (Non-Reasoning): 54.7 (#38), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
LMArena Non-English1440—
LMArena Chinese1481—
LMArena French1477—
LMArena German1463—
LMArena Japanese1450—
LMArena Korean1417—
LMArena Russian1457—
LMArena Spanish1442—

Instruction Following Not comparable

Grok 4.20 (Non-Reasoning): 75.0 (#79), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
LMArena Instruction Following1420—

Long Context Not comparable

Grok 4.20 (Non-Reasoning): 45.4 (#33), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
CL-bench22.2%—
CL-bench Life11.9%—
LMArena Longer Query1436—

Writing & Preference Not comparable

Grok 4.20 (Non-Reasoning): 65.9 (#42), Nova 2.0 Pro Preview: —

BenchmarkGrok 4.20 (Non-Reasoning)Nova 2.0 Pro Preview
LMArena Text1451—
LMArena Creative Writing1439—
EQ-Bench Creative Writing1574—
LMArena Multi-Turn1456—

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Nova 2.0 Pro Preview?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 32.8 on the Noometry Index.

Is Grok 4.20 (Non-Reasoning) or Nova 2.0 Pro Preview better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 40.2 in the Noometry coding category.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Nova 2.0 Pro Preview share?

0 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Nova 2.0 Pro Preview has 3.

Related comparisons

Go deeper