Model comparison
GPT-3.5-turbo vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 34.8 to 23.1 on the Noometry Index. GPT-3.5-turbo costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-3.5-turbo scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 32.4 to 6.0.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 128K tokens versus 16K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 23.1 | 34.8 |
| Released | 2023-03-01 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 16K | 128K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $1.50 | $5 |
| Results tracked | 44 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
GPT-3.5-turbo: 23.5 (#326), Magistral Medium: 38.6 (#161)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Coding | 1137 | 1319 |
| SciCode | — | 39.2% |
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Magistral Medium: —
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning GPT-3.5-turbo leads
GPT-3.5-turbo: 13.3 (#328), Magistral Medium: 8.7 (#342)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1108 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| Epoch Capabilities Index | 118.48 | — |
| ForecastBench | 50.4 | — |
| WinoGrande | 81.6% | — |
Math Magistral Medium leads
GPT-3.5-turbo: 6.0 (#321), Magistral Medium: 32.4 (#187)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Math | 1142 | 1249 |
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Magistral Medium leads
GPT-3.5-turbo: 10.0 (#298), Magistral Medium: 32.9 (#199)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Expert | 1070 | 1222 |
| GPQA Diamond | 28% | — |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multilingual Magistral Medium leads
GPT-3.5-turbo: 31.6 (#253), Magistral Medium: 39.8 (#219)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1108 | 1232 |
| LMArena Chinese | 1075 | 1225 |
| LMArena French | 1117 | 1268 |
| LMArena German | 1090 | 1248 |
| LMArena Japanese | 1043 | 1176 |
| LMArena Korean | 1019 | 1125 |
| LMArena Russian | 1123 | 1224 |
| LMArena Spanish | 1120 | 1269 |
Instruction Following Magistral Medium leads
GPT-3.5-turbo: 58.1 (#257), Magistral Medium: 66.2 (#207)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1119 | 1254 |
Long Context Magistral Medium leads
GPT-3.5-turbo: 34.0 (#249), Magistral Medium: 39.3 (#178)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1121 | 1295 |
Writing & Preference Magistral Medium leads
GPT-3.5-turbo: 25.4 (#300), Magistral Medium: 46.5 (#214)
| Benchmark | GPT-3.5-turbo | Magistral Medium |
|---|---|---|
| LMArena Text | 1125 | 1255 |
| LMArena Creative Writing | 1092 | 1245 |
| LMArena Multi-Turn | 1117 | 1275 |
| EQ-Bench Creative Writing | 451 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 34.8 to 23.1 on the Noometry Index. GPT-3.5-turbo costs 3.7× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, GPT-3.5-turbo or Magistral Medium?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Magistral Medium lists at $2 and $5.
Is GPT-3.5-turbo or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 38.6 versus 23.5 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 128K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and Magistral Medium share?
17 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Magistral Medium has 22.