Model comparison
Magistral Medium vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 35.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
Mistral AISummary
- They share 9 benchmarks with published results for both. Magistral Medium scores higher in 4 categories and Mercury in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury leads 17.5 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 21.6% for Mercury.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Mercury | |
|---|---|---|
| Provider | Mistral AI | Inception |
| Noometry Index | 35.2 | 37.6 |
| Released | 2025-03-17 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Medium: 39.1 (#161), Mercury: 38.7 (#170)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Coding | 1319 | 1322 |
| SciCode | 39.2% | — |
Reasoning Mercury leads
Magistral Medium: 8.6 (#348), Mercury: 17.5 (#293)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 21.6% |
| LMArena Hard Prompts | 1267 | 1285 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Not comparable
Magistral Medium: 35.1 (#189), Mercury: —
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Math | 1250 | — |
Knowledge Not comparable
Magistral Medium: 33.5 (#202), Mercury: —
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Expert | 1223 | — |
Multilingual Mercury leads
Magistral Medium: 39.6 (#224), Mercury: 41.6 (#206)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Non-English | 1232 | 1260 |
| LMArena Chinese | 1227 | — |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Too close to call
Magistral Medium: 66.0 (#211), Mercury: 65.2 (#224)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Instruction Following | 1254 | 1239 |
Long Context Too close to call
Magistral Medium: 39.3 (#183), Mercury: 38.4 (#198)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Longer Query | 1295 | 1266 |
Writing & Preference Too close to call
Magistral Medium: 46.3 (#219), Mercury: 46.2 (#221)
| Benchmark | Magistral Medium | Mercury |
|---|---|---|
| LMArena Text | 1255 | 1282 |
| LMArena Creative Writing | 1245 | 1191 |
| LMArena Multi-Turn | 1275 | 1282 |
Frequently asked questions
Is Magistral Medium better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 35.2 on the Noometry Index.
Is Magistral Medium or Mercury better for coding?
They score almost the same on coding (39.1 vs 38.7); test both on your own repository before choosing.
How many benchmarks do Magistral Medium and Mercury share?
9 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mercury has 9.