Model comparison
Grok 4 Fast vs Qwen2-72B
Grok 4 Fast is the stronger model overall, scoring 39.4 to 30.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Grok 4 Fast scores higher in 8 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 36.1.
- The biggest single-benchmark swing is WeirdML: 42.9% for Grok 4 Fast and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Grok 4 Fast | Qwen2-72B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.4 | 30.0 |
| Released | 2025-09-19 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 Fast leads
Grok 4 Fast: 32.5 (#271), Qwen2-72B: 29.1 (#310)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| WeirdML | 42.9% | 11.3% |
| LMArena Coding | 1429 | 1196 |
| LMArena WebDev | 1159 | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Grok 4 Fast leads
Grok 4 Fast: 29.5 (#86), Qwen2-72B: 17.0 (#146)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| τ²-bench Banking | 15.7% | — |
| Cybench | 30% | — |
| LMArena Search | 1171 | — |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Grok 4 Fast: 22.2 (#201), Qwen2-72B: 23.2 (#181)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1412 | 1191 |
| Epoch Capabilities Index | 144.2 | 125.28 |
| ARC-AGI-2 | 5.3% | — |
| Kagi LLM Benchmark | 66.1% | — |
| ARC-AGI-1 | 48.5% | — |
| DTBench | 82.7% | — |
| ForecastBench | 60.5 | — |
Math Grok 4 Fast leads
Grok 4 Fast: 38.9 (#123), Qwen2-72B: 30.2 (#236)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Math | 1419 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Grok 4 Fast leads
Grok 4 Fast: 32.0 (#214), Qwen2-72B: 21.2 (#275)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1411 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 19.7% | — |
| MMLU | — | 82.4% |
Multilingual Grok 4 Fast leads
Grok 4 Fast: 51.3 (#111), Qwen2-72B: 35.9 (#244)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1396 | 1176 |
| LMArena Chinese | 1457 | 1240 |
| LMArena French | 1431 | 1170 |
| LMArena German | 1383 | 1151 |
| LMArena Japanese | 1352 | 1111 |
| LMArena Korean | 1357 | 1083 |
| LMArena Russian | 1389 | 1169 |
| LMArena Spanish | 1415 | 1169 |
Instruction Following Grok 4 Fast leads
Grok 4 Fast: 73.2 (#121), Qwen2-72B: 61.7 (#241)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1387 | 1181 |
Long Context Grok 4 Fast leads
Grok 4 Fast: 63.2 (#3), Qwen2-72B: 36.1 (#235)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1415 | 1192 |
| Fiction.LiveBench | 94.4% | — |
Writing & Preference Grok 4 Fast leads
Grok 4 Fast: 60.0 (#102), Qwen2-72B: 40.8 (#241)
| Benchmark | Grok 4 Fast | Qwen2-72B |
|---|---|---|
| LMArena Text | 1407 | 1203 |
| LMArena Creative Writing | 1387 | 1181 |
| LMArena Multi-Turn | 1414 | 1196 |
Frequently asked questions
Is Grok 4 Fast better than Qwen2-72B?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 30.0 on the Noometry Index.
Is Grok 4 Fast or Qwen2-72B better for coding?
Grok 4 Fast scores higher on coding benchmarks: 32.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Grok 4 Fast and Qwen2-72B share?
19 benchmarks have published results for both models. Grok 4 Fast has 30 scored results on Noometry and Qwen2-72B has 26.