Model comparison
Mistral Small vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 33.4 on the Noometry Index. Mistral Small costs 2.3× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Mistral Small scores higher in 4 categories and Qwen Plus in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Plus leads 28.4 to 19.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.8% for Mistral Small and 63.3% for Qwen Plus.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Mistral Small | Qwen Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 37.1 |
| Released | 2024-02-26 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 256K | 33K |
| Input $ / M tokens | $0.15 | $0.40 |
| Output $ / M tokens | $0.60 | $1.20 |
| Results tracked | 39 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Mistral Small: 34.0 (#247), Qwen Plus: 38.9 (#167)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Coding | 1362 | 1328 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Qwen Plus: —
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Qwen Plus leads
Mistral Small: 19.8 (#250), Qwen Plus: 28.4 (#107)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 63.3% |
| LMArena Hard Prompts | 1335 | 1317 |
| DTBench | 70.9% | 81.1% |
| LMCA | 20.6% | 24% |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| LiveBench Data Analysis | 53.7% | — |
| LiveBench | 44% | — |
Math Qwen Plus leads
Mistral Small: 16.4 (#293), Qwen Plus: 23.3 (#271)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 17.8% |
| LMArena Math | 1341 | 1326 |
| MATH Level 5 | 46.8% | 65.3% |
| LiveBench Math | 39.9% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Mistral Small leads
Mistral Small: 31.0 (#222), Qwen Plus: 27.4 (#251)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| GPQA Diamond | 47.5% | 48.1% |
| LMArena Expert | 1291 | 1328 |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Qwen Plus: —
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Too close to call
Mistral Small: 45.5 (#169), Qwen Plus: 45.1 (#175)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1315 | 1310 |
| LMArena Chinese | 1340 | 1347 |
| LMArena Japanese | 1275 | 1251 |
| LMArena Russian | 1324 | 1323 |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Korean | 1259 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Qwen Plus leads
Mistral Small: 66.4 (#209), Qwen Plus: 68.8 (#181)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1310 | 1303 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Too close to call
Mistral Small: 40.4 (#156), Qwen Plus: 40.3 (#158)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1327 | 1324 |
Writing & Preference Too close to call
Mistral Small: 52.5 (#171), Qwen Plus: 52.2 (#176)
| Benchmark | Mistral Small | Qwen Plus |
|---|---|---|
| LMArena Text | 1338 | 1326 |
| LMArena Creative Writing | 1305 | 1293 |
| LMArena Multi-Turn | 1344 | 1336 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 33.4 on the Noometry Index. Mistral Small costs 2.3× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or Qwen Plus?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Mistral Small or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 262K.
How many benchmarks do Mistral Small and Qwen Plus share?
19 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen Plus has 20.