# GPT-3.5-turbo vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 4.0× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-3-5-turbo-vs-mistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Mistral Medium in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 25.3.
- The biggest single-benchmark swing is MATH Level 5: 15.9% for GPT-3.5-turbo and 81.6% for Mistral Medium.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 16K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 23.2 | 36.3 |
| Rank | 350 | 218 |
| Context | 16K | 262K |
| Input $/M | $0.50 | $1.50 |
| Output $/M | $1.50 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-3.5-turbo: 23.9 (#331)
- Mistral Medium: 34.2 (#243)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| WeirdML | 3.5% | 43.7% |
| LMArena Coding | 1136 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |

## Agentic & Tool Use

- GPT-3.5-turbo: —
- Mistral Medium: 28.3 (#90)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| METR Time Horizons | 21.5% | — |

## Reasoning

- GPT-3.5-turbo: 13.8 (#332)
- Mistral Medium: 24.0 (#167)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1426 |
| DTBench | 48.5% | 75.5% |
| LMCA | 9.7% | 26.1% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| Surface Evolver Bench | — | 26.9% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.55 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |

## Math

- GPT-3.5-turbo: 6.3 (#327)
- Mistral Medium: 28.1 (#245)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.2% | 32.2% |
| LMArena Math | 1142 | 1408 |
| MATH Level 5 | 15.9% | 81.6% |
| FrontierMath (Tiers 1-3) | 0% | — |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 57.8% | — |

## Knowledge

- GPT-3.5-turbo: 10.0 (#303)
- Mistral Medium: 25.0 (#265)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| GPQA Diamond | 28% | 59.5% |
| LMArena Expert | 1070 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |

## Multimodal

- GPT-3.5-turbo: —
- Mistral Medium: 35.3 (#88)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- GPT-3.5-turbo: 31.5 (#258)
- Mistral Medium: 52.1 (#91)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1108 | 1408 |
| LMArena Chinese | 1075 | 1447 |
| LMArena French | 1118 | 1459 |
| LMArena German | 1090 | 1432 |
| LMArena Japanese | 1043 | 1378 |
| LMArena Korean | 1019 | 1380 |
| LMArena Russian | 1123 | 1411 |
| LMArena Spanish | 1121 | 1433 |

## Instruction Following

- GPT-3.5-turbo: 57.9 (#262)
- Mistral Medium: 73.7 (#116)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1119 | 1398 |

## Long Context

- GPT-3.5-turbo: 34.0 (#254)
- Mistral Medium: 42.9 (#114)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1121 | 1406 |

## Writing & Preference

- GPT-3.5-turbo: 25.3 (#305)
- Mistral Medium: 60.0 (#103)

| Benchmark | GPT-3.5-turbo | Mistral Medium |
|---|---|---|
| LMArena Text | 1125 | 1424 |
| LMArena Creative Writing | 1092 | 1391 |
| LMArena Multi-Turn | 1117 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 451 | — |

## FAQ

### Is GPT-3.5-turbo better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.3 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 4.0× less per token, which makes it the better buy when Mistral Medium's lead doesn't matter for your workload.

### Which is cheaper, GPT-3.5-turbo or Mistral Medium?

GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is GPT-3.5-turbo or Mistral Medium better for coding?

Mistral Medium scores higher on coding benchmarks: 34.2 versus 23.9 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium does, with 262K tokens against 16K.

### How many benchmarks do GPT-3.5-turbo and Mistral Medium share?

23 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Mistral Medium has 36.