Model comparison
Mistral 7B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 23.0 on the Noometry Index. Mistral 7B costs 2.4× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 30.7.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 65.3% for Qwen Plus.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| Mistral 7B | Qwen Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 23.0 | 37.1 |
| Released | 2023-09-27 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 8K | 1M |
| Max output | 8K | 33K |
| Input $ / M tokens | $0.25 | $0.40 |
| Output $ / M tokens | $0.25 | $1.20 |
| Results tracked | 37 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Mistral 7B: 26.4 (#326), Qwen Plus: 38.9 (#167)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1082 | 1328 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Qwen Plus leads
Mistral 7B: 13.1 (#336), Qwen Plus: 28.4 (#107)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1317 |
| DTBench | 42.5% | 81.1% |
| Kagi LLM Benchmark | — | 63.3% |
| Chess Puzzles | 0% | — |
| LMCA | — | 24% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Qwen Plus leads
Mistral 7B: 8.1 (#325), Qwen Plus: 23.3 (#271)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 17.8% |
| LMArena Math | 1085 | 1326 |
| MATH Level 5 | 3.7% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 54.4% | — |
Knowledge Qwen Plus leads
Mistral 7B: 7.4 (#311), Qwen Plus: 27.4 (#251)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 15.2% | 48.1% |
| LMArena Expert | 1036 | 1328 |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Qwen Plus leads
Mistral 7B: 25.8 (#283), Qwen Plus: 45.1 (#175)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1012 | 1310 |
| LMArena Chinese | 1009 | 1347 |
| LMArena Japanese | 878 | 1251 |
| LMArena Russian | 1018 | 1323 |
| LMArena French | 1037 | — |
| LMArena German | 987 | — |
| LMArena Spanish | 1026 | — |
Instruction Following Qwen Plus leads
Mistral 7B: 54.2 (#280), Qwen Plus: 68.8 (#181)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1060 | 1303 |
Long Context Qwen Plus leads
Mistral 7B: 32.2 (#271), Qwen Plus: 40.3 (#158)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1060 | 1324 |
Writing & Preference Qwen Plus leads
Mistral 7B: 30.7 (#286), Qwen Plus: 52.2 (#176)
| Benchmark | Mistral 7B | Qwen Plus |
|---|---|---|
| LMArena Text | 1090 | 1326 |
| LMArena Creative Writing | 1068 | 1293 |
| LMArena Multi-Turn | 1062 | 1336 |
Frequently asked questions
Is Mistral 7B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 23.0 on the Noometry Index. Mistral 7B costs 2.4× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Qwen Plus?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Mistral 7B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 8K.
How many benchmarks do Mistral 7B and Qwen Plus share?
17 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Qwen Plus has 20.