Model comparison
GPT-5 Pro vs Magistral Medium
GPT-5 Pro is the stronger model overall, scoring 46.4 to 35.2 on the Noometry Index. Magistral Medium costs 15× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AISummary
- They share 3 benchmarks with published results for both. GPT-5 Pro scores higher in 4 categories and Magistral Medium in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 70.2% for GPT-5 Pro and 6.1% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Pro | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 46.4 | 35.2 |
| Released | 2025-10-06 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 272K | 16K |
| Input $ / M tokens | $15 | $2 |
| Output $ / M tokens | $120 | $5 |
| Results tracked | 12 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 44.0 (#80), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| SciCode | — | 39.2% |
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1319 |
| AlgoTune | 1.31 | — |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 38.9 (#62), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 18.3% | 0% |
| Kagi LLM Benchmark | 76.8% | 16.2% |
| ARC-AGI-1 | 70.2% | 6.1% |
| SimpleBench | 61.6% | — |
| CritPt | — | 0.3% |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1267 |
| Epoch Capabilities Index | 150.28 | — |
Math GPT-5 Pro leads
GPT-5 Pro: 48.5 (#63), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| LMArena Math | — | 1250 |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.7 (#42), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| Humanity's Last Exam | 31.6% | — |
| LMArena Expert | — | 1223 |
Multilingual Not comparable
GPT-5 Pro: —, Magistral Medium: 39.6 (#224)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| LMArena Non-English | — | 1232 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |
Instruction Following Not comparable
GPT-5 Pro: —, Magistral Medium: 66.0 (#211)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
GPT-5 Pro: —, Magistral Medium: 39.3 (#183)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |
Writing & Preference Not comparable
GPT-5 Pro: —, Magistral Medium: 46.3 (#219)
| Benchmark | GPT-5 Pro | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |
Frequently asked questions
Is GPT-5 Pro better than Magistral Medium?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 35.2 on the Noometry Index. Magistral Medium costs 15× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Pro or Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Pro or Magistral Medium better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Pro and Magistral Medium share?
3 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Magistral Medium has 22.