Model comparison
Mistral Large vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 31.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Mistral Large scores higher in 1 category and Qwen Plus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Plus leads 28.4 to 15.8.
- The biggest single-benchmark swing is DTBench: 65.1% for Mistral Large and 81.1% for Qwen Plus.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- Qwen Plus accepts more context: 1M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 37.1 |
| Released | 2024-02-26 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 33K |
| Input $ / M tokens | $2 | $0.40 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 51 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Mistral Large: 34.3 (#240), Qwen Plus: 38.9 (#167)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Coding | 1277 | 1328 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen Plus: —
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Qwen Plus leads
Mistral Large: 15.8 (#310), Qwen Plus: 28.4 (#107)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1317 |
| DTBench | 65.1% | 81.1% |
| LMCA | 16.7% | 24% |
| SimpleBench | 22.5% | — |
| Kagi LLM Benchmark | — | 63.3% |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| LiveBench Data Analysis | 50.1% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen Plus leads
Mistral Large: 18.2 (#291), Qwen Plus: 23.3 (#271)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 17.8% |
| LMArena Math | 1262 | 1326 |
| MATH Level 5 | 50.3% | 65.3% |
| FrontierMath (Feb 2025 set) | 0.3% | 1.7% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
Knowledge Mistral Large leads
Mistral Large: 30.1 (#230), Qwen Plus: 27.4 (#251)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| GPQA Diamond | 51.3% | 48.1% |
| LMArena Expert | 1232 | 1328 |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen Plus leads
Mistral Large: 40.0 (#219), Qwen Plus: 45.1 (#175)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1237 | 1310 |
| LMArena Chinese | 1240 | 1347 |
| LMArena Japanese | 1188 | 1251 |
| LMArena Russian | 1257 | 1323 |
| LMArena French | 1325 | — |
| LMArena German | 1254 | — |
| LMArena Korean | 1202 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Too close to call
Mistral Large: 67.9 (#191), Qwen Plus: 68.8 (#181)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1249 | 1303 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen Plus leads
Mistral Large: 38.3 (#199), Qwen Plus: 40.3 (#158)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1261 | 1324 |
Writing & Preference Qwen Plus leads
Mistral Large: 40.7 (#242), Qwen Plus: 52.2 (#176)
| Benchmark | Mistral Large | Qwen Plus |
|---|---|---|
| LMArena Text | 1266 | 1326 |
| LMArena Creative Writing | 1243 | 1293 |
| LMArena Multi-Turn | 1260 | 1336 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen Plus?
Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 131K.
How many benchmarks do Mistral Large and Qwen Plus share?
19 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen Plus has 20.