Model comparison
Grok 2 Mini 2024 08 13 vs Qwen2.5-VL 72B Instruct
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.0 to 29.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Grok 2 Mini 2024 08 13 leads 23.7 to 20.0.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 37.0 | 29.4 |
| Released | 2024-08-13 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $2.80 |
| Output $ / M tokens | — | $8.40 |
| Results tracked | 17 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 2 Mini 2024 08 13: 36.4 (#194), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Coding | 1269 | — |
Agentic & Tool Use Not comparable
Grok 2 Mini 2024 08 13: —, Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning Grok 2 Mini 2024 08 13 leads
Grok 2 Mini 2024 08 13: 23.7 (#162), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| LMArena Hard Prompts | 1255 | — |
Math Not comparable
Grok 2 Mini 2024 08 13: 32.8 (#185), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Math | 1265 | — |
Knowledge Not comparable
Grok 2 Mini 2024 08 13: 33.4 (#195), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Expert | 1238 | — |
Multimodal Not comparable
Grok 2 Mini 2024 08 13: —, Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
Grok 2 Mini 2024 08 13: 41.6 (#203), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1257 | — |
| LMArena Chinese | 1262 | — |
| LMArena French | 1285 | — |
| LMArena German | 1273 | — |
| LMArena Japanese | 1213 | — |
| LMArena Korean | 1195 | — |
| LMArena Russian | 1261 | — |
| LMArena Spanish | 1278 | — |
Instruction Following Not comparable
Grok 2 Mini 2024 08 13: 65.7 (#215), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1245 | — |
Long Context Not comparable
Grok 2 Mini 2024 08 13: 38.4 (#191), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1267 | — |
Writing & Preference Not comparable
Grok 2 Mini 2024 08 13: 47.5 (#207), Qwen2.5-VL 72B Instruct: —
| Benchmark | Grok 2 Mini 2024 08 13 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1281 | — |
| LMArena Creative Writing | 1242 | — |
| LMArena Multi-Turn | 1265 | — |
Frequently asked questions
Is Grok 2 Mini 2024 08 13 better than Qwen2.5-VL 72B Instruct?
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.0 to 29.4 on the Noometry Index.
How many benchmarks do Grok 2 Mini 2024 08 13 and Qwen2.5-VL 72B Instruct share?
0 benchmarks have published results for both models. Grok 2 Mini 2024 08 13 has 17 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.