Model comparison
Grok-3 mini vs Qwen1.5-32B
Grok-3 mini is the stronger model overall, scoring 41.2 to 30.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Qwen1.5-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 76.3% for Grok-3 mini and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Qwen1.5-32B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 30.5 |
| Released | 2025-04-09 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1379 | 1155 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Grok-3 mini: 13.6 (#334), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1130 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1386 | 1155 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 76.3% | 30.7% |
| LMArena Expert | 1395 | 1126 |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| MMLU | — | 74.4% |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1352 | 1106 |
| LMArena Chinese | 1387 | 1177 |
| LMArena French | 1357 | 1101 |
| LMArena German | 1349 | 1058 |
| LMArena Japanese | 1342 | 1027 |
| LMArena Korean | 1335 | 1008 |
| LMArena Russian | 1353 | 1073 |
| LMArena Spanish | 1381 | 1089 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1357 | 1116 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#147), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1372 | 1146 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.5 (#169), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Grok-3 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1370 | 1137 |
| LMArena Creative Writing | 1342 | 1083 |
| LMArena Multi-Turn | 1355 | 1140 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Qwen1.5-32B?
Grok-3 mini is the stronger model overall, scoring 41.2 to 30.5 on the Noometry Index.
Is Grok-3 mini or Qwen1.5-32B better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 31.7 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Qwen1.5-32B share?
18 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen1.5-32B has 21.