Model comparison
Mixtral 8x22B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 27.1 on the Noometry Index.
Last verified . 20 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Mixtral 8x22B scores higher in 1 category and Qwen3.7 Plus in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 34.1% for Mixtral 8x22B and 87.9% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Qwen3.7 Plus accepts more context: 1M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 45.3 |
| Released | 2024-04-17 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 64K | 1M |
| Max output | 64K | 131K |
| Input $ / M tokens | $2 | $0.40 |
| Output $ / M tokens | $6 | $1.60 |
| Results tracked | 34 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Mixtral 8x22B: 24.2 (#329), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1166 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Mixtral 8x22B leads
Mixtral 8x22B: 23.1 (#127), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
| Cybench | 7.5% | — |
Reasoning Qwen3.7 Plus leads
Mixtral 8x22B: 19.9 (#248), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1460 |
| DTBench | 55.1% | 84% |
| Epoch Capabilities Index | 122.03 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| LMCA | — | 37.6% |
| ForecastBench | 56.3 | — |
Math Qwen3.7 Plus leads
Mixtral 8x22B: 22.9 (#275), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1184 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Qwen3.7 Plus leads
Mixtral 8x22B: 15.1 (#293), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 34.1% | 87.9% |
| LMArena Expert | 1113 | 1467 |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multimodal Not comparable
Mixtral 8x22B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Mixtral 8x22B: 32.8 (#255), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1128 | 1445 |
| LMArena Chinese | 1116 | 1510 |
| LMArena French | 1166 | 1473 |
| LMArena German | 1141 | 1471 |
| LMArena Japanese | 1037 | 1413 |
| LMArena Korean | 1057 | 1415 |
| LMArena Russian | 1158 | 1457 |
| LMArena Spanish | 1151 | 1457 |
Instruction Following Qwen3.7 Plus leads
Mixtral 8x22B: 57.7 (#266), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1147 | 1440 |
| IFEval | 72.4% | — |
Long Context Qwen3.7 Plus leads
Mixtral 8x22B: 34.7 (#247), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1144 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Mixtral 8x22B: 36.9 (#262), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Mixtral 8x22B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1162 | 1455 |
| LMArena Creative Writing | 1141 | 1439 |
| LMArena Multi-Turn | 1130 | 1460 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 27.1 on the Noometry Index.
Which is cheaper, Mixtral 8x22B or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Mixtral 8x22B or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 24.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 64K.
How many benchmarks do Mixtral 8x22B and Qwen3.7 Plus share?
20 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen3.7 Plus has 32.