Model comparison
Mistral vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 29.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Mistral scores higher in 0 categories and Qwen3-Next 80B-A3B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.8 to 16.6.
- The biggest single-benchmark swing is MMLU-Pro: 27.7% for Mistral and 78.6% for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| Mistral | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 43.0 |
| Released | — | 2025-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2 |
| Results tracked | 22 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
Mistral: 33.8 (#250), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1162 | 1440 |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Mistral: 22.2 (#200), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
Math Qwen3-Next 80B-A3B Instruct leads
Mistral: 22.3 (#278), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Omni-MATH | 7.2% | 46.7% |
| LMArena Math | 1180 | 1440 |
Knowledge Qwen3-Next 80B-A3B Instruct leads
Mistral: 16.6 (#288), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| MMLU-Pro | 27.7% | 78.6% |
| GPQA (HELM) | 30.3% | 63% |
| LMArena Expert | 1125 | 1417 |
| Vectara Hallucination Rate | — | 9.3% |
Multilingual Qwen3-Next 80B-A3B Instruct leads
Mistral: 32.8 (#254), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1129 | 1407 |
| LMArena Chinese | 1109 | 1460 |
| LMArena French | 1180 | 1413 |
| LMArena German | 1155 | 1417 |
| LMArena Japanese | 1013 | 1395 |
| LMArena Korean | 1032 | 1364 |
| LMArena Russian | 1168 | 1404 |
| LMArena Spanish | 1143 | 1435 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
Mistral: 52.6 (#288), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| IFEval | 56.8% | 81% |
| LMArena Instruction Following | 1152 | 1389 |
Long Context Qwen3-Next 80B-A3B Instruct leads
Mistral: 35.0 (#245), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1153 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
Mistral: 37.0 (#260), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | Mistral | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1165 | 1417 |
| LMArena Creative Writing | 1158 | 1334 |
| WildBench | 66% | 80.7% |
| LMArena Multi-Turn | 1147 | 1416 |
Frequently asked questions
Is Mistral better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 29.9 on the Noometry Index.
Is Mistral or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 33.8 in the Noometry coding category.
How many benchmarks do Mistral and Qwen3-Next 80B-A3B Instruct share?
22 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.