# Gemini 3.1 Pro Preview vs Mistral Small

> Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 33.1 on the Noometry Index. Mistral Small costs 17× 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-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 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 256K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 56.7 | 33.1 |
| Rank | 20 | 238 |
| Context | 1.05M | 256K |
| Input $/M | $2 | $0.15 |
| Output $/M | $12 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.1 Pro Preview: 42.7 (#88)
- Mistral Small: 33.5 (#242)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| SciCode | 58.9% | 26.5% |
| LMArena Coding | 1483 | 1363 |
| ALE-Bench | 1,161 | 497.62 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1446 | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| MirrorCode | 8.9% | — |
| BigCodeBench Complete | — | 46.6% |
| AlgoTune | 2.02 | — |

## Agentic & Tool Use

- Gemini 3.1 Pro Preview: 37.7 (#33)
- Mistral Small: 27.9 (#87)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| 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)
- Mistral Small: 19.3 (#238)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| CritPt | 17.7% | 0% |
| LMArena Hard Prompts | 1484 | 1336 |
| DTBench | 97.1% | 70.9% |
| LMCA | 53.8% | 20.6% |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 34% | — |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 154.92 | — |
| ForecastBench | 59 | — |
| LiveBench | — | 44% |

## Math

- Gemini 3.1 Pro Preview: 61.8 (#28)
- Mistral Small: 15.4 (#287)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 5.8% |
| LMArena Math | 1485 | 1341 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |

## Knowledge

- Gemini 3.1 Pro Preview: 71.8 (#3)
- Mistral Small: 30.9 (#214)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| GPQA Diamond | 94.4% | 47.5% |
| Vectara Hallucination Rate | 10.4% | 5.1% |
| LMArena Expert | 1484 | 1293 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| MMLU | — | 68.7% |

## Multimodal

- Gemini 3.1 Pro Preview: 38.1 (#60)
- Mistral Small: 32.9 (#91)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| LMArena Vision | 1296 | 1142 |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |

## Multilingual

- Gemini 3.1 Pro Preview: 57.1 (#11)
- Mistral Small: 45.7 (#164)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| LMArena Non-English | 1475 | 1315 |
| LMArena Chinese | 1528 | 1342 |
| LMArena French | 1488 | 1337 |
| LMArena German | 1491 | 1341 |
| LMArena Japanese | 1494 | 1275 |
| LMArena Korean | 1458 | 1260 |
| LMArena Russian | 1496 | 1324 |
| LMArena Spanish | 1480 | 1346 |

## Instruction Following

- Gemini 3.1 Pro Preview: 77.1 (#31)
- Mistral Small: 66.6 (#204)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1465 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Gemini 3.1 Pro Preview: 47.3 (#17)
- Mistral Small: 40.4 (#151)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1482 | 1327 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |

## Writing & Preference

- Gemini 3.1 Pro Preview: 66.3 (#36)
- Mistral Small: 52.6 (#165)

| Benchmark | Gemini 3.1 Pro Preview | Mistral Small |
|---|---|---|
| LMArena Text | 1480 | 1338 |
| LMArena Creative Writing | 1482 | 1304 |
| LMArena Multi-Turn | 1486 | 1344 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Gemini 3.1 Pro Preview better than Mistral Small?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 33.1 on the Noometry Index. Mistral Small costs 17× 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 Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

### Is Gemini 3.1 Pro Preview or Mistral Small better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 256K.

### How many benchmarks do Gemini 3.1 Pro Preview and Mistral Small share?

26 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Mistral Small has 39.