Noometry

Model comparison

Grok 4 vs Nova Premier 1.0

Grok 4 is the stronger model overall, scoring 48.1 to 38.3 on the Noometry Index.

Last verified . 6 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Summary

  • They share 6 benchmarks with published results for both. Grok 4 scores higher in 5 categories and Nova Premier 1.0 in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 4 leads 53.8 to 35.8.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 73.6% for Grok 4 and 44.8% for Nova Premier 1.0.

Side by side

Grok 4Nova Premier 1.0
ProviderxAIAmazon
Noometry Index48.138.3
Released2025-07-092025-04-30
WeightsProprietaryProprietary
Context window—1M
Max output—10K
Input $ / M tokens—$2.50
Output $ / M tokens—$12.50
Results tracked486

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

Category by category

Coding Not comparable

Grok 4: 50.3 (#46), Nova Premier 1.0: —

BenchmarkGrok 4Nova Premier 1.0
Aider Polyglot79.6%—
WeirdML45.7%—
LMArena Coding1408—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Nova Premier 1.0: —

BenchmarkGrok 4Nova Premier 1.0
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), Nova Premier 1.0: 23.0 (#185)

BenchmarkGrok 4Nova Premier 1.0
Kagi LLM Benchmark73.6%44.8%
ARC-AGI-216%—
SimpleBench60.5%—
ARC-AGI-166.7%—
Chess Puzzles28%—
LMArena Hard Prompts1409—
Epoch Capabilities Index146.44—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Nova Premier 1.0: 33.8 (#199)

BenchmarkGrok 4Nova Premier 1.0
Omni-MATH60.3%35%
OTIS Mock AIME 2024-202584%—
LMArena Math1422—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Nova Premier 1.0: 35.8 (#180)

BenchmarkGrok 4Nova Premier 1.0
MMLU-Pro85.1%72.6%
GPQA (HELM)72.7%51.8%
GPQA Diamond87%—
Confabulations12.4%—
LMArena Expert1415—

Multimodal Not comparable

Grok 4: 33.7 (#94), Nova Premier 1.0: —

BenchmarkGrok 4Nova Premier 1.0
LMArena Vision1210—
GeoBench45%—

Multilingual Not comparable

Grok 4: 51.8 (#103), Nova Premier 1.0: —

BenchmarkGrok 4Nova Premier 1.0
LMArena Non-English1403—
LMArena Chinese1427—
LMArena French1418—
LMArena German1429—
LMArena Japanese1394—
LMArena Korean1377—
LMArena Russian1410—
LMArena Spanish1420—

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Nova Premier 1.0: 66.8 (#204)

BenchmarkGrok 4Nova Premier 1.0
IFEval94.9%80.3%
LMArena Instruction Following1387—

Long Context Not comparable

Grok 4: 63.1 (#4), Nova Premier 1.0: —

BenchmarkGrok 4Nova Premier 1.0
Fiction.LiveBench94.4%—
LMArena Longer Query1409—

Writing & Preference Grok 4 leads

Grok 4: 58.5 (#116), Nova Premier 1.0: 51.0 (#178)

BenchmarkGrok 4Nova Premier 1.0
WildBench79.7%78.8%
LMArena Text1411—
LMArena Creative Writing1397—
Short-Story Creative Writing76.9%—
LMArena Multi-Turn1416—

Frequently asked questions

Is Grok 4 better than Nova Premier 1.0?

Grok 4 is the stronger model overall, scoring 48.1 to 38.3 on the Noometry Index.

How many benchmarks do Grok 4 and Nova Premier 1.0 share?

6 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Nova Premier 1.0 has 6.

Related comparisons

Go deeper