Model comparison
Mistral Large 3 vs Mixtral 8x22B
Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 7 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 36.9.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Mistral Large 3 accepts more context: 262K tokens versus 64K.
Side by side
| Mistral Large 3 | Mixtral 8x22B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 39.1 | 27.1 |
| Released | 2025-12-02 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 262K | 64K |
| Max output | 8K | 64K |
| Input $ / M tokens | $0.25 | $2 |
| Output $ / M tokens | $0.75 | $6 |
| Results tracked | 24 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Mistral Large 3: 34.4 (#237), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1448 | 1166 |
| LMArena WebDev | 1230 | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Mistral Large 3: 15.2 (#319), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1150 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Thematic Generalization | 23% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Mistral Large 3 leads
Mistral Large 3: 38.7 (#129), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1414 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
Knowledge Mistral Large 3 leads
Mistral Large 3: 36.0 (#177), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1421 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 14.5% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), Mixtral 8x22B: —
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Mistral Large 3 leads
Mistral Large 3: 52.5 (#84), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1413 | 1128 |
| LMArena Chinese | 1447 | 1116 |
| LMArena French | 1455 | 1166 |
| LMArena German | 1437 | 1141 |
| LMArena Japanese | 1394 | 1037 |
| LMArena Korean | 1384 | 1057 |
| LMArena Russian | 1411 | 1158 |
| LMArena Spanish | 1440 | 1151 |
Instruction Following Mistral Large 3 leads
Mistral Large 3: 74.0 (#108), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1403 | 1147 |
| IFEval | — | 72.4% |
Long Context Mistral Large 3 leads
Mistral Large 3: 43.1 (#105), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1413 | 1144 |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.0 (#101), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Mistral Large 3 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1428 | 1162 |
| LMArena Creative Writing | 1386 | 1141 |
| LMArena Multi-Turn | 1429 | 1130 |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | — | 71.1% |
Frequently asked questions
Is Mistral Large 3 better than Mixtral 8x22B?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
Which is cheaper, Mistral Large 3 or Mixtral 8x22B?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mistral Large 3 or Mixtral 8x22B better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 64K.
How many benchmarks do Mistral Large 3 and Mixtral 8x22B share?
17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Mixtral 8x22B has 34.