Model comparison
Magistral Medium vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AI
Arcee AISummary
- They share 19 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Trinity Large Thinking in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Trinity Large Thinking leads 16.9 to 8.6.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2 / $5 for Magistral Medium.
Side by side
| Magistral Medium | Trinity Large Thinking | |
|---|---|---|
| Provider | Mistral AI | Arcee AI |
| Noometry Index | 35.2 | 38.6 |
| Released | 2025-03-17 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 80K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $5 | $0.80 |
| Results tracked | 22 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| SciCode | 39.2% | 36.1% |
| LMArena Coding | 1319 | 1381 |
| LMArena WebDev | — | 1238 |
Reasoning Trinity Large Thinking leads
Magistral Medium: 8.6 (#348), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| CritPt | 0.3% | 0.9% |
| LMArena Hard Prompts | 1267 | 1350 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 16.5% |
| ARC-AGI-1 | 6.1% | — |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
Magistral Medium: 35.1 (#189), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1250 | 1366 |
Knowledge Trinity Large Thinking leads
Magistral Medium: 33.5 (#202), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1223 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
Multilingual Trinity Large Thinking leads
Magistral Medium: 39.6 (#224), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1232 | 1325 |
| LMArena Chinese | 1227 | 1373 |
| LMArena French | 1267 | 1374 |
| LMArena German | 1248 | 1356 |
| LMArena Japanese | 1175 | 1311 |
| LMArena Korean | 1125 | 1306 |
| LMArena Russian | 1224 | 1337 |
| LMArena Spanish | 1271 | 1357 |
Instruction Following Trinity Large Thinking leads
Magistral Medium: 66.0 (#211), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1254 | 1334 |
Long Context Trinity Large Thinking leads
Magistral Medium: 39.3 (#183), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1295 | 1355 |
Writing & Preference Trinity Large Thinking leads
Magistral Medium: 46.3 (#219), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Magistral Medium | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1255 | 1340 |
| LMArena Creative Writing | 1245 | 1320 |
| LMArena Multi-Turn | 1275 | 1342 |
Frequently asked questions
Is Magistral Medium better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Trinity Large Thinking better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Magistral Medium and Trinity Large Thinking share?
19 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Trinity Large Thinking has 24.