Model comparison
Mixtral 8x7B vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 1.6× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Qwen3.5 122B-A10B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 122B-A10B leads 38.8 to 11.0.
- The biggest single-benchmark swing is DTBench: 49.6% for Mixtral 8x7B and 84.3% for Qwen3.5 122B-A10B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 32K.
Side by side
| Mixtral 8x7B | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 42.1 |
| Released | 2023-12-11 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 32K | 262K |
| Max output | 32K | 66K |
| Input $ / M tokens | $0.70 | $0.40 |
| Output $ / M tokens | $0.70 | $3.20 |
| Results tracked | 38 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 122B-A10B leads
Mixtral 8x7B: 32.8 (#269), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1126 | 1436 |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |
Reasoning Qwen3.5 122B-A10B leads
Mixtral 8x7B: 18.2 (#285), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1421 |
| DTBench | 49.6% | 84.3% |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| LMCA | — | 32.2% |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.47 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |
Math Qwen3.5 122B-A10B leads
Mixtral 8x7B: 18.8 (#289), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1147 | 1432 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |
Knowledge Qwen3.5 122B-A10B leads
Mixtral 8x7B: 11.0 (#301), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1088 | 1432 |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| Vectara Hallucination Rate | — | 11.2% |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |
Multimodal Not comparable
Mixtral 8x7B: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Mixtral 8x7B: 29.6 (#266), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1077 | 1400 |
| LMArena Chinese | 1055 | 1462 |
| LMArena French | 1166 | 1442 |
| LMArena German | 1114 | 1426 |
| LMArena Japanese | 931 | 1367 |
| LMArena Korean | 968 | 1352 |
| LMArena Russian | 1090 | 1400 |
| LMArena Spanish | 1111 | 1424 |
Instruction Following Qwen3.5 122B-A10B leads
Mixtral 8x7B: 51.0 (#297), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1109 | 1399 |
| IFEval | 57.5% | — |
Long Context Qwen3.5 122B-A10B leads
Mixtral 8x7B: 33.4 (#260), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1103 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Mixtral 8x7B: 34.2 (#270), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Mixtral 8x7B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1132 | 1417 |
| LMArena Creative Writing | 1109 | 1368 |
| LMArena Multi-Turn | 1115 | 1416 |
| WildBench | 67.3% | — |
Frequently asked questions
Is Mixtral 8x7B better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 1.6× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Mixtral 8x7B or Qwen3.5 122B-A10B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Mixtral 8x7B or Qwen3.5 122B-A10B better for coding?
Qwen3.5 122B-A10B scores higher on coding benchmarks: 39.1 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 122B-A10B does, with 262K tokens against 32K.
How many benchmarks do Mixtral 8x7B and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen3.5 122B-A10B has 27.