Model comparison
Grok-3 mini vs Qwen-14B
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Grok-3 mini scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 52.4.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Qwen-14B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 31.4 |
| Released | 2025-04-09 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 18 |
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), Qwen-14B: 31.2 (#288)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Coding | 1379 | 1071 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Qwen-14B leads
Grok-3 mini: 13.6 (#334), Qwen-14B: 19.6 (#257)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1027 |
| Epoch Capabilities Index | 140.35 | 113.03 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Qwen-14B: 31.2 (#227)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Math | 1386 | 1068 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Grok-3 mini: 46.4 (#81), Qwen-14B: —
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Qwen-14B: 27.5 (#275)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1352 | 1041 |
| LMArena Chinese | 1387 | 1077 |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Qwen-14B: 52.4 (#289)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1357 | 1031 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#147), Qwen-14B: 31.3 (#280)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1372 | 1028 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.5 (#169), Qwen-14B: 27.6 (#299)
| Benchmark | Grok-3 mini | Qwen-14B |
|---|---|---|
| LMArena Text | 1370 | 1051 |
| LMArena Creative Writing | 1342 | 1028 |
| LMArena Multi-Turn | 1355 | 1022 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Qwen-14B?
Grok-3 mini is the stronger model overall, scoring 41.2 to 31.4 on the Noometry Index.
Is Grok-3 mini or Qwen-14B better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 31.2 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Qwen-14B share?
11 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen-14B has 18.