Model comparison
Grok 3 vs Qwen Max
Grok 3 is the stronger model overall, scoring 39.9 to 34.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Grok 3 scores higher in 6 categories and Qwen Max in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 30.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 16.1% for Qwen Max.
Side by side
| Grok 3 | Qwen Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.9 | 34.7 |
| 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 | 40 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Qwen Max: 30.7 (#292)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| Aider Polyglot | 53.3% | 21.8% |
| LMArena Coding | 1432 | 1288 |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.5 (#76), Qwen Max: —
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Qwen Max leads
Grok 3: 13.7 (#333), Qwen Max: 25.1 (#151)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1269 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.33 | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Qwen Max: 22.3 (#276)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 16.1% |
| LMArena Math | 1391 | 1275 |
| MATH Level 5 | 88.7% | 67.2% |
| FrontierMath (Feb 2025 set) | 3.8% | 1% |
| Omni-MATH | 46.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Qwen Max: 30.3 (#228)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| GPQA Diamond | 75.8% | 56.1% |
| LMArena Expert | 1421 | 1248 |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Qwen Max: 41.8 (#202)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1410 | 1263 |
| LMArena Chinese | 1448 | 1254 |
| LMArena French | 1460 | 1330 |
| LMArena German | 1431 | 1254 |
| LMArena Japanese | 1387 | 1205 |
| LMArena Korean | 1373 | 1142 |
| LMArena Russian | 1416 | 1274 |
| LMArena Spanish | 1417 | 1290 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Qwen Max: 66.5 (#208)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1409 | 1262 |
| IFEval | 88.4% | — |
Long Context Too close to call
Grok 3: 38.7 (#192), Qwen Max: 39.4 (#180)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 58.3% | 66.7% |
| LMArena Longer Query | 1439 | 1288 |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Qwen Max: 47.8 (#205)
| Benchmark | Grok 3 | Qwen Max |
|---|---|---|
| LMArena Text | 1426 | 1282 |
| LMArena Creative Writing | 1414 | 1248 |
| LMArena Multi-Turn | 1425 | 1277 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Qwen Max?
Grok 3 is the stronger model overall, scoring 39.9 to 34.7 on the Noometry Index.
Is Grok 3 or Qwen Max better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 30.7 in the Noometry coding category.
How many benchmarks do Grok 3 and Qwen Max share?
23 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen Max has 23.