Model comparison
Mistral Medium 3.5 vs Mixtral 8x22B
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral Medium 3.5 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 Mistral Medium 3.5 leads 40.0 to 15.1.
- Both cost about the same: $1.50 input and $7.50 output per million tokens.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 64K.
Side by side
| Mistral Medium 3.5 | Mixtral 8x22B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 40.2 | 27.1 |
| Released | — | 2024-04-17 |
| Weights | Open | Open |
| Context window | 262K | 64K |
| Max output | 210K | 64K |
| Input $ / M tokens | $1.50 | $2 |
| Output $ / M tokens | $7.50 | $6 |
| Results tracked | 22 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
Mistral Medium 3.5: 36.0 (#213), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1461 | 1166 |
| LMArena WebDev | 1264 | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Mistral Medium 3.5: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Mistral Medium 3.5: 17.3 (#295), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1150 |
| Epoch Capabilities Index | 141.35 | 122.03 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |
Math Mistral Medium 3.5 leads
Mistral Medium 3.5: 39.1 (#113), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1431 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Mistral Medium 3.5 leads
Mistral Medium 3.5: 40.0 (#126), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1432 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
Mistral Medium 3.5: 38.3 (#65), Mixtral 8x22B: —
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1223 | — |
Multilingual Mistral Medium 3.5 leads
Mistral Medium 3.5: 51.9 (#100), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1404 | 1128 |
| LMArena Chinese | 1442 | 1116 |
| LMArena French | 1448 | 1166 |
| LMArena German | 1451 | 1141 |
| LMArena Korean | 1385 | 1057 |
| LMArena Russian | 1395 | 1158 |
| LMArena Spanish | 1409 | 1151 |
| LMArena Japanese | — | 1037 |
Instruction Following Mistral Medium 3.5 leads
Mistral Medium 3.5: 74.6 (#90), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1415 | 1147 |
| IFEval | — | 72.4% |
Long Context Mistral Medium 3.5 leads
Mistral Medium 3.5: 43.2 (#103), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1415 | 1144 |
Writing & Preference Mistral Medium 3.5 leads
Mistral Medium 3.5: 58.5 (#117), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Mistral Medium 3.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1421 | 1162 |
| LMArena Creative Writing | 1374 | 1141 |
| LMArena Multi-Turn | 1423 | 1130 |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 993 | — |
Frequently asked questions
Is Mistral Medium 3.5 better than Mixtral 8x22B?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 27.1 on the Noometry Index.
Which is cheaper, Mistral Medium 3.5 or Mixtral 8x22B?
Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Mistral Medium 3.5 or Mixtral 8x22B better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 64K.
How many benchmarks do Mistral Medium 3.5 and Mixtral 8x22B share?
17 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Mixtral 8x22B has 34.