Noometry

Model comparison

Gemini 4 Argon vs GPT-5 Nano

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 33.5 on the Noometry Index.

Last verified . 14 shared benchmarks.

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Gemini 4 Argon scores higher in 10 categories and GPT-5 Nano in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 4 Argon leads 73.9 to 29.4.
  • The biggest single-benchmark swing is ProofBench: 99% for Gemini 4 Argon and 12% for GPT-5 Nano.

Side by side

Gemini 4 ArgonGPT-5 Nano
ProviderGoogleOpenAI
Noometry Index56.533.5
Released2026-09-302025-08-07
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.40
Results tracked2149

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

Category by category

Coding Gemini 4 Argon leads

Gemini 4 Argon: 62.0 (#9), GPT-5 Nano: 33.6 (#254)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Coding15501351
SWE-bench Verified (bash only)—34.8%
LMArena WebDev1678—
FrontierSWE55%—
SciCode61.8%—
WeirdML—38.1%
ALE-Bench—718.67

Agentic & Tool Use Gemini 4 Argon leads

Gemini 4 Argon: 49.2 (#8), GPT-5 Nano: 25.8 (#106)

BenchmarkGemini 4 ArgonGPT-5 Nano
Terminal-Bench—21.8%
APEX-Agents82.2%—
Berkeley Function Calling Leaderboard—51.5%
Vending-Bench 213,718—

Reasoning Gemini 4 Argon leads

Gemini 4 Argon: 44.2 (#47), GPT-5 Nano: 16.3 (#306)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Hard Prompts15481328
ARC-AGI-2—2.6%
Kagi LLM Benchmark—62.2%
ARC-AGI-1—20.7%
CritPt27.1%—
Chess Puzzles—27%
Mystery Game Puzzles—9%
DTBench—62.7%
LMCA—7.9%
Epoch Capabilities Index—139.38
ForecastBench—59.1

Math Gemini 4 Argon leads

Gemini 4 Argon: 73.9 (#17), GPT-5 Nano: 29.4 (#241)

BenchmarkGemini 4 ArgonGPT-5 Nano
ProofBench99%12%
LMArena Math15361317
FrontierMath (Tiers 1-3)—20%
FrontierMath Tier 4—2.4%
OTIS Mock AIME 2024-2025—81.1%
Omni-MATH—54.6%
MATH Level 5—95.2%
FrontierMath (Feb 2025 set)—8.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Gemini 4 Argon leads

Gemini 4 Argon: 43.9 (#89), GPT-5 Nano: 35.9 (#178)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Expert15531321
GPQA Diamond—69.4%
SimpleQA Verified—11.7%
MMLU-Pro—77.8%
Vectara Hallucination Rate—10.5%
GPQA (HELM)—67.9%

Multimodal Gemini 4 Argon leads

Gemini 4 Argon: 46.5 (#14), GPT-5 Nano: 31.3 (#108)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Vision—1159
VPCT—37.2%
Blueprint-Bench 254.4%—

Multilingual Gemini 4 Argon leads

Gemini 4 Argon: 60.3 (#1), GPT-5 Nano: 45.3 (#172)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Non-English15231313
LMArena Chinese16101356
LMArena Russian15371296
LMArena Spanish14971360
LMArena German—1327
LMArena Japanese—1226
LMArena Korean—1269

Instruction Following Gemini 4 Argon leads

Gemini 4 Argon: 80.1 (#2), GPT-5 Nano: 75.0 (#79)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Instruction Following15381306
IFEval—93.2%

Long Context Gemini 4 Argon leads

Gemini 4 Argon: 47.6 (#15), GPT-5 Nano: 31.3 (#281)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Longer Query15491312
Fiction.LiveBench—44.4%

Writing & Preference Gemini 4 Argon leads

Gemini 4 Argon: 71.4 (#19), GPT-5 Nano: 39.1 (#249)

BenchmarkGemini 4 ArgonGPT-5 Nano
LMArena Text15341320
LMArena Creative Writing15311249
LMArena Multi-Turn15571311
EQ-Bench Creative Writing—705
WildBench—80.6%

Frequently asked questions

Is Gemini 4 Argon better than GPT-5 Nano?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 33.5 on the Noometry Index.

Is Gemini 4 Argon or GPT-5 Nano better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 33.6 in the Noometry coding category.

How many benchmarks do Gemini 4 Argon and GPT-5 Nano share?

14 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and GPT-5 Nano has 49.

Related comparisons

Go deeper