Model comparison
Mistral Small 3.1 vs Mixtral 8x22B
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 27.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Mistral Small 3.1 scores higher in 6 categories and Mixtral 8x22B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 24.2.
- The biggest single-benchmark swing is MMLU-Pro: 61% for Mistral Small 3.1 and 46% for Mixtral 8x22B.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Mistral Small 3.1 accepts more context: 128K tokens versus 64K.
Side by side
| Mistral Small 3.1 | Mixtral 8x22B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 31.7 | 27.1 |
| Released | 2025-03-17 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 128K | 64K |
| Max output | 102K | 64K |
| Input $ / M tokens | $0.35 | $2 |
| Output $ / M tokens | $0.56 | $6 |
| Results tracked | 28 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Small 3.1: 38.3 (#179), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1309 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Mistral Small 3.1: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Too close to call
Mistral Small 3.1: 19.7 (#254), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1150 |
| Epoch Capabilities Index | 127.48 | 122.03 |
| Chess Puzzles | 1% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |
Math Mixtral 8x22B leads
Mistral Small 3.1: 14.7 (#301), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 24.8% | 16.3% |
| LMArena Math | 1262 | 1184 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| MATH Level 5 | — | 24.2% |
Knowledge Mistral Small 3.1 leads
Mistral Small 3.1: 22.6 (#271), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 41.9% | 34.1% |
| MMLU-Pro | 61% | 46% |
| GPQA (HELM) | 39.2% | 33.4% |
| LMArena Expert | 1257 | 1113 |
| MMLU | — | 77.8% |
Multimodal Not comparable
Mistral Small 3.1: 33.2 (#99), Mixtral 8x22B: —
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Mistral Small 3.1 leads
Mistral Small 3.1: 41.2 (#209), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1255 | 1128 |
| LMArena Chinese | 1253 | 1116 |
| LMArena French | 1273 | 1166 |
| LMArena German | 1266 | 1141 |
| LMArena Japanese | 1208 | 1037 |
| LMArena Korean | 1206 | 1057 |
| LMArena Russian | 1263 | 1158 |
| LMArena Spanish | 1283 | 1151 |
Instruction Following Mistral Small 3.1 leads
Mistral Small 3.1: 63.6 (#230), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| IFEval | 75% | 72.4% |
| LMArena Instruction Following | 1264 | 1147 |
Long Context Mistral Small 3.1 leads
Mistral Small 3.1: 39.5 (#178), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1299 | 1144 |
Writing & Preference Too close to call
Mistral Small 3.1: 37.0 (#259), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Mistral Small 3.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1277 | 1162 |
| LMArena Creative Writing | 1253 | 1141 |
| WildBench | 78.8% | 71.1% |
| LMArena Multi-Turn | 1270 | 1130 |
| EQ-Bench Creative Writing | 761 | — |
Frequently asked questions
Is Mistral Small 3.1 better than Mixtral 8x22B?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 27.1 on the Noometry Index.
Which is cheaper, Mistral Small 3.1 or Mixtral 8x22B?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mistral Small 3.1 or Mixtral 8x22B better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Small 3.1 does, with 128K tokens against 64K.
How many benchmarks do Mistral Small 3.1 and Mixtral 8x22B share?
24 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Mixtral 8x22B has 34.