Model comparison

Grok 4.3 vs Nova 2.0 Pro Preview

Grok 4.3 is the stronger model overall, scoring 43.6 to 32.8 on the Noometry Index.

Last verified . 3 shared benchmarks.

Grok 4.3 xAI

43.6

Rank #80 Confirmed

Nova 2.0 Pro Preview Amazon

32.8

Rank #241 Reported

Summary

  • They share 3 benchmarks with published results for both. Grok 4.3 scores higher in 3 categories and Nova 2.0 Pro Preview in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.3 leads 34.9 to 21.7.
  • The biggest single-benchmark swing is CritPt: 8% for Grok 4.3 and 0% for Nova 2.0 Pro Preview.

Side by side

Grok 4.3 and Nova 2.0 Pro Preview specifications
Grok 4.3Nova 2.0 Pro Preview
ProviderxAIAmazon
Noometry Index43.632.8
Released2026-04-172025-12-02
WeightsProprietaryProprietary
Context window1M—
Max output30K—
Input $ / M tokens$1.25—
Output $ / M tokens$2.50—
Results tracked403

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

Category by category

Coding Grok 4.3 leads

Grok 4.3: 41.3 (#117), Nova 2.0 Pro Preview: 40.2 (#130)

Coding benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
SciCode47.3%42.7%
LMArena WebDev1357—
WeirdML49.9%—
LMArena Coding1415—
ALE-Bench944.17—

Agentic & Tool Use Grok 4.3 leads

Grok 4.3: 27.6 (#93), Nova 2.0 Pro Preview: 21.9 (#127)

Agentic & Tool Use benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
GDP.pdf8%2%
LMArena Search1165—
Vending-Bench 235.26—

Reasoning Grok 4.3 leads

Grok 4.3: 34.9 (#60), Nova 2.0 Pro Preview: 21.7 (#189)

Reasoning benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
CritPt8%0%
NYT Connections (extended)55.2%—
Chess Puzzles25%—
LMArena Hard Prompts1397—
DTBench90.7%—
LMCA38.3%—
Epoch Capabilities Index149.13—
ForecastBench60.3—

Math Not comparable

Grok 4.3: 45.8 (#60), Nova 2.0 Pro Preview: —

Math benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
FrontierMath (Tiers 1-3)42.8%—
FrontierMath Tier 414.6%—
OTIS Mock AIME 2024-202593.3%—
ProofBench11%—
LMArena Math1388—

Knowledge Not comparable

Grok 4.3: 52.5 (#57), Nova 2.0 Pro Preview: —

Knowledge benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
GPQA Diamond88.8%—
SimpleQA Verified33.2%—
LMArena Expert1385—

Multimodal Not comparable

Grok 4.3: 31.6 (#96), Nova 2.0 Pro Preview: —

Multimodal benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
LMArena Vision1231—
Blueprint-Bench 20%—

Multilingual Not comparable

Grok 4.3: 50.7 (#114), Nova 2.0 Pro Preview: —

Multilingual benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
LMArena Non-English1385—
LMArena Chinese1423—
LMArena French1412—
LMArena German1395—
LMArena Japanese1379—
LMArena Korean1357—
LMArena Russian1399—
LMArena Spanish1402—

Instruction Following Not comparable

Grok 4.3: 72.3 (#135), Nova 2.0 Pro Preview: —

Instruction Following benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
LMArena Instruction Following1366—

Long Context Not comparable

Grok 4.3: 42.5 (#118), Nova 2.0 Pro Preview: —

Long Context benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
LMArena Longer Query1393—

Writing & Preference Not comparable

Grok 4.3: 58.6 (#112), Nova 2.0 Pro Preview: —

Writing & Preference benchmarks
BenchmarkGrok 4.3Nova 2.0 Pro Preview
LMArena Text1397—
LMArena Creative Writing1380—
EQ-Bench 41075—
LMArena Multi-Turn1406—

Frequently asked questions

Is Grok 4.3 better than Nova 2.0 Pro Preview?

Grok 4.3 is the stronger model overall, scoring 43.6 to 32.8 on the Noometry Index.

Is Grok 4.3 or Nova 2.0 Pro Preview better for coding?

Grok 4.3 scores higher on coding benchmarks: 41.3 versus 40.2 in the Noometry coding category.

How many benchmarks do Grok 4.3 and Nova 2.0 Pro Preview share?

3 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Nova 2.0 Pro Preview has 3.

Related comparisons

Go deeper