# Gemini 4 Argon vs GPT-5.2

> Gemini 4 Argon is the stronger model overall, scoring 56.5 to 54.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-4-argon-vs-gpt-5-2
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Gemini 4 Argon scores higher in 7 categories and GPT-5.2 in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.2 leads 59.3 to 43.9.
- The biggest single-benchmark swing is ProofBench: 99% for Gemini 4 Argon and 15% for GPT-5.2.

## Snapshot

| | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 56.5 | 54.1 |
| Rank | 24 | 34 |
| Context | — | 400K |
| Input $/M | — | $1.75 |
| Output $/M | — | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 4 Argon: 62.0 (#9)
- GPT-5.2: 51.6 (#37)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena WebDev | 1678 | 1416 |
| LMArena Coding | 1550 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.7% |
| FrontierSWE | 55% | — |
| SciCode | 61.8% | — |
| GSO | — | 27.4% |
| WeirdML | — | 72.2% |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |

## Agentic & Tool Use

- Gemini 4 Argon: 49.2 (#8)
- GPT-5.2: 40.2 (#24)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| Vending-Bench 2 | 13,718 | 3,591 |
| Terminal-Bench | — | 64.9% |
| APEX-Agents | 82.2% | — |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| METR Time Horizons | — | 75.3% |

## Reasoning

- Gemini 4 Argon: 44.2 (#47)
- GPT-5.2: 50.2 (#35)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Hard Prompts | 1548 | 1445 |
| ARC-AGI-2 | — | 52.9% |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| CritPt | 27.1% | — |
| Chess Puzzles | — | 49% |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| Mystery Game Puzzles | — | 23% |
| DTBench | — | 90.9% |
| LMCA | — | 43.9% |
| Epoch Capabilities Index | — | 153.45 |
| ForecastBench | — | 60.1 |

## Math

- Gemini 4 Argon: 73.9 (#17)
- GPT-5.2: 60.0 (#38)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| ProofBench | 99% | 15% |
| LMArena Math | 1536 | 1440 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |

## Knowledge

- Gemini 4 Argon: 43.9 (#89)
- GPT-5.2: 59.3 (#32)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Expert | 1553 | 1445 |
| GPQA Diamond | — | 91.4% |
| Humanity's Last Exam | — | 27.8% |
| SimpleQA Verified | — | 37.1% |
| Vectara Hallucination Rate | — | 8.4% |

## Multimodal

- Gemini 4 Argon: 46.5 (#14)
- GPT-5.2: 51.3 (#7)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Vision | — | 1268 |
| VPCT | — | 84% |
| Blueprint-Bench 2 | 54.4% | — |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |

## Multilingual

- Gemini 4 Argon: 60.3 (#1)
- GPT-5.2: 53.4 (#67)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1523 | 1425 |
| LMArena Chinese | 1610 | 1460 |
| LMArena Russian | 1537 | 1440 |
| LMArena Spanish | 1497 | 1433 |
| LMArena French | — | 1455 |
| LMArena German | — | 1448 |
| LMArena Japanese | — | 1420 |
| LMArena Korean | — | 1392 |

## Instruction Following

- Gemini 4 Argon: 80.1 (#2)
- GPT-5.2: 74.7 (#89)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1538 | 1417 |

## Long Context

- Gemini 4 Argon: 47.6 (#15)
- GPT-5.2: 44.0 (#78)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1549 | 1428 |
| CL-bench | — | 18.2% |

## Writing & Preference

- Gemini 4 Argon: 71.4 (#19)
- GPT-5.2: 66.8 (#32)

| Benchmark | Gemini 4 Argon | GPT-5.2 |
|---|---|---|
| LMArena Text | 1534 | 1439 |
| LMArena Creative Writing | 1531 | 1401 |
| LMArena Multi-Turn | 1557 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |

## FAQ

### Is Gemini 4 Argon better than GPT-5.2?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 54.1 on the Noometry Index.

### Is Gemini 4 Argon or GPT-5.2 better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 51.6 in the Noometry coding category.

### How many benchmarks do Gemini 4 Argon and GPT-5.2 share?

16 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and GPT-5.2 has 67.