Model comparison
Grok-2 (Dec 2024) vs Qwen1.5-32B
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 30.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 53.8% for Grok-2 (Dec 2024) and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Qwen1.5-32B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 30.0 |
| Released | 2024-08-13 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 32.9 (#254), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1288 | 1155 |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | — | 32.3% |
| LiveBench Coding | 46.4% | — |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Grok-2 (Dec 2024): 16.4 (#294), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1131 |
| SimpleBench | 22.7% | — |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |
Math Qwen1.5-32B leads
Grok-2 (Dec 2024): 19.6 (#278), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1283 | 1155 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 29.8 (#225), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 53.8% | 30.7% |
| LMArena Expert | 1254 | 1126 |
| Confabulations | 20.1% | — |
| MMLU | — | 74.4% |
Multilingual Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 43.3 (#183), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1282 | 1106 |
| LMArena Chinese | 1289 | 1176 |
| LMArena French | 1317 | 1100 |
| LMArena German | 1287 | 1058 |
| LMArena Japanese | 1244 | 1027 |
| LMArena Korean | 1237 | 1007 |
| LMArena Russian | 1286 | 1073 |
| LMArena Spanish | 1281 | 1089 |
Instruction Following Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 67.1 (#197), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1116 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 38.7 (#186), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1276 | 1146 |
Writing & Preference Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 48.8 (#192), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Grok-2 (Dec 2024) | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1305 | 1137 |
| LMArena Creative Writing | 1284 | 1083 |
| LMArena Multi-Turn | 1290 | 1140 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Qwen1.5-32B?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 30.0 on the Noometry Index.
Is Grok-2 (Dec 2024) or Qwen1.5-32B better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 32.9 versus 31.1 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Qwen1.5-32B share?
18 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen1.5-32B has 21.