Model comparison
Grok-3 mini vs Qwen1.5-110B
Grok-3 mini is the stronger model overall, scoring 41.0 to 33.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Qwen1.5-110B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.7 to 60.6.
- Qwen1.5-110B has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Qwen1.5-110B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.0 | 33.6 |
| Released | 2025-04-09 | 2024-04-25 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.4 (#126), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1380 | 1184 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Qwen1.5-110B leads
Grok-3 mini: 13.8 (#323), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1168 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
| ForecastBench | — | 57.7 |
Math Grok-3 mini leads
Grok-3 mini: 40.3 (#78), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1386 | 1185 |
| 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: 46.3 (#75), Qwen1.5-110B: 30.7 (#217)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1395 | 1144 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.3 (#141), Qwen1.5-110B: 33.8 (#245)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1352 | 1142 |
| LMArena Chinese | 1387 | 1206 |
| LMArena French | 1357 | 1150 |
| LMArena German | 1350 | 1123 |
| LMArena Japanese | 1343 | 1074 |
| LMArena Korean | 1336 | 1044 |
| LMArena Russian | 1352 | 1118 |
| LMArena Spanish | 1379 | 1141 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.7 (#8), Qwen1.5-110B: 60.6 (#247)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1356 | 1158 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#142), Qwen1.5-110B: 35.0 (#237)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1372 | 1157 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.7 (#163), Qwen1.5-110B: 38.1 (#250)
| Benchmark | Grok-3 mini | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1370 | 1175 |
| LMArena Creative Writing | 1342 | 1148 |
| LMArena Multi-Turn | 1355 | 1160 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Qwen1.5-110B?
Grok-3 mini is the stronger model overall, scoring 41.0 to 33.6 on the Noometry Index.
Is Grok-3 mini or Qwen1.5-110B better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 32.4 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Qwen1.5-110B share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen1.5-110B has 20.