Model comparison
Grok 2 Mini 2024 08 13 vs Qwen2.5-Coder-32B
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.7 to 33.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Grok 2 Mini 2024 08 13 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 2 Mini 2024 08 13 leads 37.0 to 22.6.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 37.7 | 33.4 |
| Released | 2024-08-13 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 17 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 37.0 (#199), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1269 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 24.8 (#159), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1255 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 35.4 (#185), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1265 | 1251 |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Too close to call
Grok 2 Mini 2024 08 13: 33.9 (#200), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1238 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 41.4 (#208), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1257 | 1205 |
| LMArena Chinese | 1262 | 1222 |
| LMArena Russian | 1261 | 1228 |
| LMArena French | 1286 | — |
| LMArena German | 1273 | — |
| LMArena Japanese | 1213 | — |
| LMArena Korean | 1195 | — |
| LMArena Spanish | 1279 | — |
Instruction Following Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 65.5 (#220), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1245 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Too close to call
Grok 2 Mini 2024 08 13: 38.4 (#196), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1266 | 1251 |
Writing & Preference Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 47.3 (#211), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1281 | 1230 |
| LMArena Creative Writing | 1242 | 1174 |
| LMArena Multi-Turn | 1265 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Grok 2 Mini 2024 08 13 better than Qwen2.5-Coder-32B?
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.7 to 33.4 on the Noometry Index.
Is Grok 2 Mini 2024 08 13 or Qwen2.5-Coder-32B better for coding?
Grok 2 Mini 2024 08 13 scores higher on coding benchmarks: 37.0 versus 22.6 in the Noometry coding category.
How many benchmarks do Grok 2 Mini 2024 08 13 and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Grok 2 Mini 2024 08 13 has 17 scored results on Noometry and Qwen2.5-Coder-32B has 31.