Model comparison
Mistral Small 3.1 vs Mixtral 8x7B
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 7 categories and Mixtral 8x7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Small 3.1 leads 63.6 to 51.0.
- The biggest single-benchmark swing is MMLU-Pro: 61% for Mistral Small 3.1 and 33.5% for Mixtral 8x7B.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Mistral Small 3.1 accepts more context: 128K tokens versus 32K.
Side by side
| Mistral Small 3.1 | Mixtral 8x7B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 31.7 | 27.1 |
| Released | 2025-03-17 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 128K | 32K |
| Max output | 102K | 32K |
| Input $ / M tokens | $0.35 | $0.70 |
| Output $ / M tokens | $0.56 | $0.70 |
| Results tracked | 28 | 38 |
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 8x7B: 32.8 (#269)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1309 | 1126 |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning Mistral Small 3.1 leads
Mistral Small 3.1: 19.7 (#254), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1115 |
| Epoch Capabilities Index | 127.48 | 118.47 |
| Chess Puzzles | 1% | — |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Mixtral 8x7B leads
Mistral Small 3.1: 14.7 (#301), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 24.8% | 10.5% |
| LMArena Math | 1262 | 1147 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Mistral Small 3.1 leads
Mistral Small 3.1: 22.6 (#271), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 41.9% | 30.6% |
| MMLU-Pro | 61% | 33.5% |
| GPQA (HELM) | 39.2% | 29.6% |
| LMArena Expert | 1257 | 1088 |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
Mistral Small 3.1: 33.2 (#99), Mixtral 8x7B: —
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Mistral Small 3.1 leads
Mistral Small 3.1: 41.2 (#209), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1255 | 1077 |
| LMArena Chinese | 1253 | 1055 |
| LMArena French | 1273 | 1166 |
| LMArena German | 1266 | 1114 |
| LMArena Japanese | 1208 | 931 |
| LMArena Korean | 1206 | 968 |
| LMArena Russian | 1263 | 1090 |
| LMArena Spanish | 1283 | 1111 |
Instruction Following Mistral Small 3.1 leads
Mistral Small 3.1: 63.6 (#230), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| IFEval | 75% | 57.5% |
| LMArena Instruction Following | 1264 | 1109 |
Long Context Mistral Small 3.1 leads
Mistral Small 3.1: 39.5 (#178), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1299 | 1103 |
Writing & Preference Mistral Small 3.1 leads
Mistral Small 3.1: 37.0 (#259), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Mistral Small 3.1 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1277 | 1132 |
| LMArena Creative Writing | 1253 | 1109 |
| WildBench | 78.8% | 67.3% |
| LMArena Multi-Turn | 1270 | 1115 |
| EQ-Bench Creative Writing | 761 | — |
Frequently asked questions
Is Mistral Small 3.1 better than Mixtral 8x7B?
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 8x7B?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.
Is Mistral Small 3.1 or Mixtral 8x7B better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Small 3.1 does, with 128K tokens against 32K.
How many benchmarks do Mistral Small 3.1 and Mixtral 8x7B share?
24 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Mixtral 8x7B has 38.