Model comparison
Mistral Nemo vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 26.4 on the Noometry Index. Mistral Nemo costs 5.0× less per token, which makes it the better buy when Qwen2.5-Coder-32B's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Mistral Nemo scores higher in 0 categories and Qwen2.5-Coder-32B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 12.3.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Mistral Nemo accepts more context: 128K tokens versus 33K.
Side by side
| Mistral Nemo | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.4 | 33.4 |
| Released | 2024-07-01 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 128K | 33K |
| Max output | 128K | 29K |
| Input $ / M tokens | $0.15 | $0.66 |
| Output $ / M tokens | $0.15 | $1 |
| Results tracked | 10 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| LMArena Coding | — | 1276 |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), Qwen2.5-Coder-32B: —
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Too close to call
Mistral Nemo: 20.7 (#232), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| Epoch Capabilities Index | 118.68 | 119.49 |
| LiveBench Reasoning | — | 42.1% |
| LMArena Hard Prompts | — | 1251 |
| DTBench | 48.6% | — |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| PIQA | 83.5% | — |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
Mistral Nemo: 25.5 (#268), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| GSM8K | 84.2% | 93% |
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
| MATH Level 5 | 10.8% | — |
Knowledge Qwen2.5-Coder-32B leads
Mistral Nemo: 12.3 (#298), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| GPQA Diamond | 29.9% | — |
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| BoolQ | 82.5% | — |
| MMLU | — | 79.1% |
Multilingual Not comparable
Mistral Nemo: —, Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | — | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Not comparable
Mistral Nemo: —, Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | — | 58.7% |
| LMArena Instruction Following | — | 1223 |
Long Context Not comparable
Mistral Nemo: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Mistral Nemo: 28.5 (#296), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Mistral Nemo | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | — | 1230 |
| LMArena Creative Writing | — | 1174 |
| EQ-Bench Creative Writing | 881 | — |
| LMArena Multi-Turn | — | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Mistral Nemo better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 26.4 on the Noometry Index. Mistral Nemo costs 5.0× less per token, which makes it the better buy when Qwen2.5-Coder-32B's lead doesn't matter for your workload.
Which is cheaper, Mistral Nemo or Qwen2.5-Coder-32B?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Which has the bigger context window?
Mistral Nemo does, with 128K tokens against 33K.
How many benchmarks do Mistral Nemo and Qwen2.5-Coder-32B share?
2 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen2.5-Coder-32B has 31.