Model comparison
Grok 4 Fast vs Qwen1.5-72B
Grok 4 Fast is the stronger model overall, scoring 39.4 to 30.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Grok 4 Fast scores higher in 8 categories and Qwen1.5-72B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 35.1.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| Grok 4 Fast | Qwen1.5-72B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.4 | 30.8 |
| Released | 2025-09-19 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4 Fast: 32.5 (#271), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1429 | 1165 |
| LMArena WebDev | 1159 | — |
| WeirdML | 42.9% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Grok 4 Fast: 29.5 (#86), Qwen1.5-72B: —
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| τ²-bench Banking | 15.7% | — |
| Cybench | 30% | — |
| LMArena Search | 1171 | — |
Reasoning Too close to call
Grok 4 Fast: 22.2 (#201), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1412 | 1148 |
| ARC-AGI-2 | 5.3% | — |
| Kagi LLM Benchmark | 66.1% | — |
| ARC-AGI-1 | 48.5% | — |
| DTBench | 82.7% | — |
| Epoch Capabilities Index | 144.2 | — |
| ForecastBench | 60.5 | — |
Math Grok 4 Fast leads
Grok 4 Fast: 38.9 (#123), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1419 | 1164 |
Knowledge Grok 4 Fast leads
Grok 4 Fast: 32.0 (#214), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1411 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 19.7% | — |
Multilingual Grok 4 Fast leads
Grok 4 Fast: 51.3 (#111), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1396 | 1135 |
| LMArena Chinese | 1457 | 1186 |
| LMArena French | 1431 | 1159 |
| LMArena German | 1383 | 1084 |
| LMArena Japanese | 1352 | 1061 |
| LMArena Korean | 1357 | 1050 |
| LMArena Russian | 1389 | 1104 |
| LMArena Spanish | 1415 | 1110 |
Instruction Following Grok 4 Fast leads
Grok 4 Fast: 73.2 (#121), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1387 | 1141 |
Long Context Grok 4 Fast leads
Grok 4 Fast: 63.2 (#3), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1415 | 1157 |
| Fiction.LiveBench | 94.4% | — |
Writing & Preference Grok 4 Fast leads
Grok 4 Fast: 60.0 (#102), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Grok 4 Fast | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1407 | 1166 |
| LMArena Creative Writing | 1387 | 1137 |
| LMArena Multi-Turn | 1414 | 1160 |
Frequently asked questions
Is Grok 4 Fast better than Qwen1.5-72B?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 30.8 on the Noometry Index.
Is Grok 4 Fast or Qwen1.5-72B better for coding?
They score almost the same on coding (32.5 vs 31.9); test both on your own repository before choosing.
How many benchmarks do Grok 4 Fast and Qwen1.5-72B share?
17 benchmarks have published results for both models. Grok 4 Fast has 30 scored results on Noometry and Qwen1.5-72B has 22.