# Gemini 4 Argon vs Mistral Medium

> Gemini 4 Argon is the stronger model overall, scoring 56.5 to 36.3 on the Noometry Index.

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

## Summary

- They share 16 benchmarks with published results for both. Gemini 4 Argon scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 28.1.
- The biggest single-benchmark swing is ProofBench: 99% for Gemini 4 Argon and 9% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 56.5 | 36.3 |
| Rank | 24 | 218 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Gemini 4 Argon: 62.0 (#9)
- Mistral Medium: 34.2 (#243)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| SciCode | 61.8% | 40.2% |
| LMArena Coding | 1550 | 1434 |
| FrontierCode | — | 8% |
| LMArena WebDev | 1678 | — |
| FrontierSWE | 55% | — |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Gemini 4 Argon: 49.2 (#8)
- Mistral Medium: 28.3 (#90)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| APEX-Agents | 82.2% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| Vending-Bench 2 | 13,718 | — |

## Reasoning

- Gemini 4 Argon: 44.2 (#47)
- Mistral Medium: 24.0 (#167)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| CritPt | 27.1% | 0% |
| LMArena Hard Prompts | 1548 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |

## Math

- Gemini 4 Argon: 73.9 (#17)
- Mistral Medium: 28.1 (#245)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| ProofBench | 99% | 9% |
| LMArena Math | 1536 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Gemini 4 Argon: 43.9 (#89)
- Mistral Medium: 25.0 (#265)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Expert | 1553 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |

## Multimodal

- Gemini 4 Argon: 46.5 (#14)
- Mistral Medium: 35.3 (#88)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
| Blueprint-Bench 2 | 54.4% | — |

## Multilingual

- Gemini 4 Argon: 60.3 (#1)
- Mistral Medium: 52.1 (#91)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1523 | 1408 |
| LMArena Chinese | 1610 | 1447 |
| LMArena Russian | 1537 | 1411 |
| LMArena Spanish | 1497 | 1433 |
| LMArena French | — | 1459 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1380 |

## Instruction Following

- Gemini 4 Argon: 80.1 (#2)
- Mistral Medium: 73.7 (#116)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1538 | 1398 |

## Long Context

- Gemini 4 Argon: 47.6 (#15)
- Mistral Medium: 42.9 (#114)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1549 | 1406 |

## Writing & Preference

- Gemini 4 Argon: 71.4 (#19)
- Mistral Medium: 60.0 (#103)

| Benchmark | Gemini 4 Argon | Mistral Medium |
|---|---|---|
| LMArena Text | 1534 | 1424 |
| LMArena Creative Writing | 1531 | 1391 |
| LMArena Multi-Turn | 1557 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Gemini 4 Argon better than Mistral Medium?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 36.3 on the Noometry Index.

### Is Gemini 4 Argon or Mistral Medium better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 34.2 in the Noometry coding category.

### How many benchmarks do Gemini 4 Argon and Mistral Medium share?

16 benchmarks have published results for both models. Gemini 4 Argon has 21 scored results on Noometry and Mistral Medium has 36.