Model comparison
Grok-2 (Dec 2024) vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 33.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 4 categories and Qwen Max in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Max leads 25.1 to 16.9.
Side by side
| Grok-2 (Dec 2024) | Qwen Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.7 | 34.7 |
| Released | 2024-08-13 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 33.3 (#258), Qwen Max: 30.7 (#292)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Coding | 1287 | 1288 |
| Aider Polyglot | — | 21.8% |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
Reasoning Qwen Max leads
Grok-2 (Dec 2024): 16.9 (#299), Qwen Max: 25.1 (#151)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1269 |
| SimpleBench | 22.7% | — |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |
Math Qwen Max leads
Grok-2 (Dec 2024): 20.8 (#284), Qwen Max: 22.3 (#276)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 16.1% |
| LMArena Math | 1283 | 1275 |
| MATH Level 5 | 63.5% | 67.2% |
| FrontierMath (Feb 2025 set) | 0.7% | 1% |
| LiveBench Math | 54.9% | — |
Knowledge Too close to call
Grok-2 (Dec 2024): 29.8 (#233), Qwen Max: 30.3 (#228)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| GPQA Diamond | 53.8% | 56.1% |
| LMArena Expert | 1254 | 1248 |
| Confabulations | 20.1% | — |
Multilingual Grok-2 (Dec 2024) leads
Grok-2 (Dec 2024): 43.1 (#188), Qwen Max: 41.8 (#202)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Non-English | 1282 | 1263 |
| LMArena Chinese | 1289 | 1254 |
| LMArena French | 1318 | 1330 |
| LMArena German | 1287 | 1254 |
| LMArena Japanese | 1244 | 1205 |
| LMArena Korean | 1237 | 1142 |
| LMArena Russian | 1286 | 1274 |
| LMArena Spanish | 1281 | 1290 |
Instruction Following Too close to call
Grok-2 (Dec 2024): 66.9 (#202), Qwen Max: 66.5 (#208)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1270 | 1262 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Too close to call
Grok-2 (Dec 2024): 38.8 (#190), Qwen Max: 39.4 (#180)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1276 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Too close to call
Grok-2 (Dec 2024): 48.6 (#198), Qwen Max: 47.8 (#205)
| Benchmark | Grok-2 (Dec 2024) | Qwen Max |
|---|---|---|
| LMArena Text | 1305 | 1282 |
| LMArena Creative Writing | 1284 | 1248 |
| LMArena Multi-Turn | 1290 | 1277 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Qwen Max better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 30.7 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Qwen Max share?
21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen Max has 23.