# GPT-5.5 vs Mistral Medium 3.1

> GPT-5.5 is the stronger model overall, scoring 63.4 to 31.5 on the Noometry Index. Mistral Medium 3.1 costs 14× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-5-vs-mistral-medium-3-1
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GPT-5.5 scores higher in 2 categories and Mistral Medium 3.1 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 leads 72.7 to 10.1.
- The biggest single-benchmark swing is NYT Connections (extended): 96.2% for GPT-5.5 and 6.5% for Mistral Medium 3.1.
- Mistral Medium 3.1 is cheaper at $0.40 / $2 per million input/output tokens, against $5 / $30 for GPT-5.5.
- GPT-5.5 accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 63.4 | 31.5 |
| Rank | 8 | 260 |
| Context | 1.05M | 131K |
| Input $/M | $5 | $0.40 |
| Output $/M | $30 | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.5: 58.3 (#13)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| SWE-bench Verified | 80.6% | — |
| DeepSWE | 67% | — |
| FrontierCode | 43% | — |
| LMArena WebDev | 1512 | — |
| SciCode | 56.1% | — |
| GSO | 40.2% | — |
| WeirdML | 84.9% | — |
| LMArena Coding | 1494 | — |
| MirrorCode | 10% | — |
| ALE-Bench | 1,943 | — |

## Agentic & Tool Use

- GPT-5.5: 50.7 (#6)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| Terminal-Bench | 84.7% | — |
| APEX-Agents | 55.1% | — |
| OSWorld 2.0 | 13% | — |
| Remote Labor Index | 6.3% | — |
| τ²-bench Banking | 44.6% | — |
| DeepResearch Bench | 54% | — |
| PostTrainBench | 27.2% | — |
| ExploitBench | 47.4% | — |
| GBAEval | 53.2% | — |
| GDP.pdf | 26% | — |
| LMArena Search | 1242 | — |
| Vending-Bench 2 | 7,524 | — |

## Reasoning

- GPT-5.5: 72.7 (#8)
- Mistral Medium 3.1: 10.1 (#336)

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| NYT Connections (extended) | 96.2% | 6.5% |
| ARC-AGI-2 | 85% | — |
| SimpleBench | 69% | — |
| Kagi LLM Benchmark | 88.8% | — |
| ARC-AGI-1 | 95% | — |
| CritPt | 27.1% | — |
| Chess Puzzles | 54% | — |
| Thematic Generalization | — | 20.3% |
| EBR-Bench | 34.3% | — |
| LMArena Hard Prompts | 1489 | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 96% | — |
| LMCA | 54.3% | — |
| Surface Evolver Bench | 88.1% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 159.25 | — |
| ForecastBench | 60.6 | — |

## Math

- GPT-5.5: 81.5 (#9)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.3% | — |
| FrontierMath Tier 4 | 72.5% | — |
| MathArena Final-Answer Competitions | 94.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 50% | — |
| LMArena Math | 1486 | — |
| FrontierMath (Feb 2025 set) | 51.7% | — |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | 35.4% | — |

## Knowledge

- GPT-5.5: 64.4 (#14)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 63% | — |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1508 | — |

## Multimodal

- GPT-5.5: 47.1 (#11)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 36.2% | — |
| Furniture Assembly | 44.2% | — |
| LMArena Document | 1486 | — |

## Multilingual

- GPT-5.5: 56.5 (#19)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| LMArena Non-English | 1467 | — |
| LMArena Chinese | 1535 | — |
| LMArena French | 1486 | — |
| LMArena German | 1478 | — |
| LMArena Japanese | 1498 | — |
| LMArena Korean | 1461 | — |
| LMArena Russian | 1473 | — |
| LMArena Spanish | 1469 | — |

## Instruction Following

- GPT-5.5: 77.7 (#18)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| LMArena Instruction Following | 1479 | — |

## Long Context

- GPT-5.5: 48.3 (#12)
- Mistral Medium 3.1: —

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| CL-bench Life | 22.2% | — |
| LMArena Longer Query | 1484 | — |

## Writing & Preference

- GPT-5.5: 72.8 (#13)
- Mistral Medium 3.1: 55.6 (#140)

| Benchmark | GPT-5.5 | Mistral Medium 3.1 |
|---|---|---|
| EQ-Bench Creative Writing | 1844 | 1476 |
| LMArena Text | 1471 | — |
| LMArena Creative Writing | 1455 | — |
| EQ-Bench 4 | 1315 | — |
| LMArena Multi-Turn | 1477 | — |

## FAQ

### Is GPT-5.5 better than Mistral Medium 3.1?

GPT-5.5 is the stronger model overall, scoring 63.4 to 31.5 on the Noometry Index. Mistral Medium 3.1 costs 14× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.5 or Mistral Medium 3.1?

Mistral Medium 3.1 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; GPT-5.5 lists at $5 and $30.

### Which has the bigger context window?

GPT-5.5 does, with 1.05M tokens against 131K.

### How many benchmarks do GPT-5.5 and Mistral Medium 3.1 share?

2 benchmarks have published results for both models. GPT-5.5 has 71 scored results on Noometry and Mistral Medium 3.1 has 3.