Model comparison
Grok-3 mini vs Qwen Max
Grok-3 mini is the stronger model overall, scoring 41.0 to 34.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 40.3 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 16.1% for Qwen Max.
Side by side
| Grok-3 mini | Qwen Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.0 | 34.4 |
| Released | 2025-04-09 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 35 | 23 |
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), Qwen Max: 30.3 (#288)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| Aider Polyglot | 49.3% | 21.8% |
| LMArena Coding | 1380 | 1288 |
| WeirdML | 42.6% | — |
Reasoning Qwen Max leads
Grok-3 mini: 13.8 (#323), Qwen Max: 24.1 (#154)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1270 |
| 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: 40.3 (#78), Qwen Max: 21.0 (#272)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 16.1% |
| LMArena Math | 1386 | 1275 |
| MATH Level 5 | 90.9% | 67.2% |
| FrontierMath (Feb 2025 set) | 5.9% | 1% |
| Omni-MATH | 31.8% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.3 (#75), Qwen Max: 30.3 (#222)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| GPQA Diamond | 76.3% | 56.1% |
| LMArena Expert | 1395 | 1248 |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.3 (#141), Qwen Max: 42.0 (#197)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| LMArena Non-English | 1352 | 1263 |
| LMArena Chinese | 1387 | 1254 |
| LMArena French | 1357 | 1329 |
| LMArena German | 1350 | 1254 |
| LMArena Japanese | 1343 | 1205 |
| LMArena Korean | 1336 | 1141 |
| LMArena Russian | 1352 | 1274 |
| LMArena Spanish | 1379 | 1290 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.7 (#8), Qwen Max: 66.7 (#203)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1356 | 1262 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#142), Qwen Max: 39.4 (#175)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 66.7% | 66.7% |
| LMArena Longer Query | 1372 | 1289 |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.7 (#163), Qwen Max: 48.0 (#200)
| Benchmark | Grok-3 mini | Qwen Max |
|---|---|---|
| LMArena Text | 1370 | 1282 |
| LMArena Creative Writing | 1342 | 1248 |
| LMArena Multi-Turn | 1355 | 1277 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Qwen Max?
Grok-3 mini is the stronger model overall, scoring 41.0 to 34.4 on the Noometry Index.
Is Grok-3 mini or Qwen Max better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 30.3 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Qwen Max share?
23 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen Max has 23.