Model comparison
Magistral Medium vs Mixtral 8x22B
Magistral Medium is the stronger model overall, scoring 35.2 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 15.1.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Magistral Medium accepts more context: 262K tokens versus 64K.
Side by side
| Magistral Medium | Mixtral 8x22B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 27.1 |
| Released | 2025-03-17 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 262K | 64K |
| Max output | 16K | 64K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $5 | $6 |
| Results tracked | 22 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1319 | 1166 |
| SciCode | 39.2% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Magistral Medium: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Magistral Medium: 8.6 (#348), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1150 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1250 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1223 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1232 | 1128 |
| LMArena Chinese | 1227 | 1116 |
| LMArena French | 1267 | 1166 |
| LMArena German | 1248 | 1141 |
| LMArena Japanese | 1175 | 1037 |
| LMArena Korean | 1125 | 1057 |
| LMArena Russian | 1224 | 1158 |
| LMArena Spanish | 1271 | 1151 |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1147 |
| IFEval | — | 72.4% |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1295 | 1144 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Magistral Medium | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1255 | 1162 |
| LMArena Creative Writing | 1245 | 1141 |
| LMArena Multi-Turn | 1275 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Magistral Medium better than Mixtral 8x22B?
Magistral Medium is the stronger model overall, scoring 35.2 to 27.1 on the Noometry Index.
Which is cheaper, Magistral Medium or Mixtral 8x22B?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Magistral Medium or Mixtral 8x22B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 64K.
How many benchmarks do Magistral Medium and Mixtral 8x22B share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mixtral 8x22B has 34.