# Gemini 4 Argon vs GPT-5 Mini

> Gemini 4 Argon is the stronger model overall, scoring 56.5 to 41.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-4-argon-vs-gpt-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemini 4 Argon scores higher in 9 categories and GPT-5 Mini in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 46.7.
- The biggest single-benchmark swing is ProofBench: 99% for Gemini 4 Argon and 9% for GPT-5 Mini.

## Snapshot

| | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 56.5 | 41.8 |
| Rank | 24 | 128 |
| Context | — | 400K |
| Input $/M | — | $0.25 |
| Output $/M | — | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 4 Argon: 62.0 (#9)
- GPT-5 Mini: 40.1 (#146)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| SciCode | 61.8% | 39.2% |
| LMArena Coding | 1550 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| LMArena WebDev | 1678 | — |
| SWE-bench Multilingual | — | 39.7% |
| FrontierSWE | 55% | — |
| WeirdML | — | 52.7% |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |

## Agentic & Tool Use

- Gemini 4 Argon: 49.2 (#8)
- GPT-5 Mini: 31.1 (#70)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| Vending-Bench 2 | 13,718 | -31.18 |
| Terminal-Bench | — | 34.8% |
| APEX-Agents | 82.2% | — |
| Berkeley Function Calling Leaderboard | — | 55.5% |

## Reasoning

- Gemini 4 Argon: 44.2 (#47)
- GPT-5 Mini: 23.9 (#168)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| CritPt | 27.1% | 0% |
| LMArena Hard Prompts | 1548 | 1380 |
| ARC-AGI-2 | — | 4.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| Epoch Capabilities Index | — | 145.52 |
| ForecastBench | — | 61 |

## Math

- Gemini 4 Argon: 73.9 (#17)
- GPT-5 Mini: 46.7 (#69)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| ProofBench | 99% | 9% |
| LMArena Math | 1536 | 1378 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Gemini 4 Argon: 43.9 (#89)
- GPT-5 Mini: 45.6 (#86)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Expert | 1553 | 1379 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |

## Multimodal

- Gemini 4 Argon: 46.5 (#14)
- GPT-5 Mini: 35.6 (#85)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |
| Blueprint-Bench 2 | 54.4% | — |

## Multilingual

- Gemini 4 Argon: 60.3 (#1)
- GPT-5 Mini: 48.9 (#137)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1523 | 1363 |
| LMArena Chinese | 1610 | 1385 |
| LMArena Russian | 1537 | 1362 |
| LMArena Spanish | 1497 | 1355 |
| LMArena French | — | 1386 |
| LMArena German | — | 1366 |
| LMArena Japanese | — | 1341 |
| LMArena Korean | — | 1308 |

## Instruction Following

- Gemini 4 Argon: 80.1 (#2)
- GPT-5 Mini: 76.2 (#46)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1538 | 1357 |
| IFEval | — | 92.7% |

## Long Context

- Gemini 4 Argon: 47.6 (#15)
- GPT-5 Mini: 41.9 (#132)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1549 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- Gemini 4 Argon: 71.4 (#19)
- GPT-5 Mini: 55.2 (#148)

| Benchmark | Gemini 4 Argon | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1534 | 1373 |
| LMArena Creative Writing | 1531 | 1325 |
| LMArena Multi-Turn | 1557 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |

## FAQ

### Is Gemini 4 Argon better than GPT-5 Mini?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 41.8 on the Noometry Index.

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

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 40.1 in the Noometry coding category.

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

17 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and GPT-5 Mini has 60.