Model comparison
Grok 3 vs Qwen1.5-72B
Grok 3 is the stronger model overall, scoring 39.6 to 30.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Grok 3 scores higher in 7 categories and Qwen1.5-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.0 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for Grok 3 and 28.8% for Qwen1.5-72B.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Qwen1.5-72B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 30.3 |
| Released | 2025-04-09 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Grok 3: 41.5 (#113), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1432 | 1166 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), Qwen1.5-72B: —
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Qwen1.5-72B leads
Grok 3: 13.8 (#322), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1148 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.34 | — |
Math Grok 3 leads
Grok 3: 36.2 (#122), Qwen1.5-72B: 30.7 (#205)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1390 | 1164 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Qwen1.5-72B: 11.5 (#295)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 75.8% | 28.8% |
| LMArena Expert | 1420 | 1136 |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Qwen1.5-72B: 33.4 (#248)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1411 | 1135 |
| LMArena Chinese | 1448 | 1186 |
| LMArena French | 1460 | 1158 |
| LMArena German | 1431 | 1084 |
| LMArena Japanese | 1389 | 1061 |
| LMArena Korean | 1374 | 1049 |
| LMArena Russian | 1416 | 1104 |
| LMArena Spanish | 1417 | 1110 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Qwen1.5-72B: 59.6 (#251)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1409 | 1142 |
| IFEval | 88.4% | — |
Long Context Grok 3 leads
Grok 3: 38.7 (#187), Qwen1.5-72B: 35.0 (#238)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1439 | 1157 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Grok 3 leads
Grok 3: 56.0 (#136), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Grok 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1426 | 1166 |
| LMArena Creative Writing | 1414 | 1137 |
| LMArena Multi-Turn | 1424 | 1160 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Qwen1.5-72B?
Grok 3 is the stronger model overall, scoring 39.6 to 30.3 on the Noometry Index.
Is Grok 3 or Qwen1.5-72B better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 31.4 in the Noometry coding category.
How many benchmarks do Grok 3 and Qwen1.5-72B share?
18 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen1.5-72B has 22.