# Gemini 3.1 Pro Preview vs Magistral Medium

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-1-pro-preview-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 8.7.
- The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 6.1% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 56.7 | 34.8 |
| Rank | 20 | 224 |
| Context | 1.05M | 128K |
| Input $/M | $2 | $2 |
| Output $/M | $12 | $5 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.7 (#88)
- Magistral Medium: 38.6 (#161)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| SciCode | 58.9% | 39.2% |
| LMArena Coding | 1483 | 1319 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1446 | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#33)
- Magistral Medium: —

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |

## Reasoning

- Gemini 3.1 Pro Preview: 71.7 (#9)
- Magistral Medium: 8.7 (#342)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 77.1% | 0% |
| ARC-AGI-1 | 98% | 6.1% |
| CritPt | 17.7% | 0.3% |
| LMArena Hard Prompts | 1484 | 1267 |
| SimpleBench | 79.6% | — |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 97.4% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.92 | — |
| ForecastBench | 59 | — |

## Math

- Gemini 3.1 Pro Preview: 61.8 (#28)
- Magistral Medium: 32.4 (#187)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Math | 1485 | 1249 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Magistral Medium: 32.9 (#199)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Expert | 1484 | 1222 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |

## Multimodal

- Gemini 3.1 Pro Preview: 38.1 (#60)
- Magistral Medium: —

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.1 (#11)
- Magistral Medium: 39.8 (#219)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1475 | 1232 |
| LMArena Chinese | 1528 | 1225 |
| LMArena French | 1488 | 1268 |
| LMArena German | 1491 | 1248 |
| LMArena Japanese | 1494 | 1176 |
| LMArena Korean | 1458 | 1125 |
| LMArena Russian | 1496 | 1224 |
| LMArena Spanish | 1480 | 1269 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.1 (#31)
- Magistral Medium: 66.2 (#207)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1465 | 1254 |

## Long Context

- Gemini 3.1 Pro Preview: 47.3 (#17)
- Magistral Medium: 39.3 (#178)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1482 | 1295 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.3 (#36)
- Magistral Medium: 46.5 (#214)

| Benchmark | Gemini 3.1 Pro Preview | Magistral Medium |
|---|---|---|
| LMArena Text | 1480 | 1255 |
| LMArena Creative Writing | 1482 | 1245 |
| LMArena Multi-Turn | 1486 | 1275 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |

## FAQ

### Is Gemini 3.1 Pro Preview better than Magistral Medium?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.1 Pro Preview or Magistral Medium?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Magistral Medium better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.

### How many benchmarks do Gemini 3.1 Pro Preview and Magistral Medium share?

21 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Magistral Medium has 22.