Model comparison
GPT-4.5 vs Magistral Medium
GPT-4.5 is the stronger model overall, scoring 37.2 to 35.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. GPT-4.5 scores higher in 6 categories and Magistral Medium in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4.5 leads 52.5 to 39.6.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 37.2 | 35.2 |
| Released | 2025-02-27 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 42 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Coding | 1396 | 1319 |
| Aider Polyglot | 44.9% | — |
| SciCode | — | 39.2% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Magistral Medium: —
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning GPT-4.5 leads
GPT-4.5: 13.9 (#330), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 0.8% | 0% |
| ARC-AGI-1 | 10.3% | 6.1% |
| LMArena Hard Prompts | 1403 | 1267 |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 16.2% |
| CritPt | — | 0.3% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Magistral Medium leads
GPT-4.5: 32.6 (#211), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Math | 1412 | 1250 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Magistral Medium leads
GPT-4.5: 32.5 (#211), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1394 | 1223 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
Multimodal Not comparable
GPT-4.5: 37.6 (#71), Magistral Medium: —
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.5 (#83), Magistral Medium: 39.6 (#224)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1413 | 1232 |
| LMArena Chinese | 1421 | 1227 |
| LMArena French | 1418 | 1267 |
| LMArena German | 1457 | 1248 |
| LMArena Japanese | 1416 | 1175 |
| LMArena Korean | 1392 | 1125 |
| LMArena Russian | 1419 | 1224 |
| LMArena Spanish | — | 1271 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.6 (#134), Magistral Medium: 66.0 (#211)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1404 | 1254 |
| LiveBench Instruction Following | 72.3% | — |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#155), Magistral Medium: 39.3 (#183)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1406 | 1295 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 56.9 (#134), Magistral Medium: 46.3 (#219)
| Benchmark | GPT-4.5 | Magistral Medium |
|---|---|---|
| LMArena Text | 1417 | 1255 |
| LMArena Creative Writing | 1394 | 1245 |
| LMArena Multi-Turn | 1444 | 1275 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Magistral Medium?
GPT-4.5 is the stronger model overall, scoring 37.2 to 35.2 on the Noometry Index.
Is GPT-4.5 or Magistral Medium better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 39.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Magistral Medium share?
18 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Magistral Medium has 22.