Model comparison
Grok 3 vs Qwen2-72B
Grok 3 is the stronger model overall, scoring 39.9 to 30.0 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Grok 3 scores higher in 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.2 to 21.2.
- The biggest single-benchmark swing is MATH Level 5: 88.7% for Grok 3 and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Qwen2-72B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.9 | 30.0 |
| Released | 2025-04-09 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.9 (#115), Qwen2-72B: 29.1 (#310)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| WeirdML | 37.2% | 11.3% |
| LMArena Coding | 1432 | 1196 |
| Aider Polyglot | 53.3% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.5 (#76), Qwen2-72B: 17.0 (#146)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| BALROG | 29.5% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Grok 3: 13.7 (#333), Qwen2-72B: 23.2 (#181)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1434 | 1191 |
| Epoch Capabilities Index | 138.33 | 125.28 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
Math Grok 3 leads
Grok 3: 38.0 (#145), Qwen2-72B: 30.2 (#236)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1391 | 1235 |
| MATH Level 5 | 88.7% | 39.1% |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.2 (#82), Qwen2-72B: 21.2 (#275)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 75.8% | 40.8% |
| LMArena Expert | 1421 | 1171 |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
| MMLU | — | 82.4% |
Multilingual Grok 3 leads
Grok 3: 52.3 (#87), Qwen2-72B: 35.9 (#244)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1410 | 1176 |
| LMArena Chinese | 1448 | 1240 |
| LMArena French | 1460 | 1170 |
| LMArena German | 1431 | 1151 |
| LMArena Japanese | 1387 | 1111 |
| LMArena Korean | 1373 | 1083 |
| LMArena Russian | 1416 | 1169 |
| LMArena Spanish | 1417 | 1169 |
Instruction Following Grok 3 leads
Grok 3: 75.0 (#73), Qwen2-72B: 61.7 (#241)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1409 | 1181 |
| IFEval | 88.4% | — |
Long Context Grok 3 leads
Grok 3: 38.7 (#192), Qwen2-72B: 36.1 (#235)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1439 | 1192 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 55.8 (#141), Qwen2-72B: 40.8 (#241)
| Benchmark | Grok 3 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1426 | 1203 |
| LMArena Creative Writing | 1414 | 1181 |
| LMArena Multi-Turn | 1425 | 1196 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Qwen2-72B?
Grok 3 is the stronger model overall, scoring 39.9 to 30.0 on the Noometry Index.
Is Grok 3 or Qwen2-72B better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 29.1 in the Noometry coding category.
How many benchmarks do Grok 3 and Qwen2-72B share?
21 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen2-72B has 26.