Model comparison
DeepSeek-V3.1 vs Grok 2 Mini 2024 08 13
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Grok 2 Mini 2024 08 13 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 47.3.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 42.8 | 37.7 |
| Released | 2025-08-21 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Grok 2 Mini 2024 08 13: 37.0 (#199)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Coding | 1417 | 1269 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Grok 2 Mini 2024 08 13: 24.8 (#159)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1255 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Grok 2 Mini 2024 08 13: 35.4 (#185)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Math | 1420 | 1265 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Grok 2 Mini 2024 08 13: 33.9 (#200)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Expert | 1405 | 1238 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Grok 2 Mini 2024 08 13: 41.4 (#208)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Non-English | 1400 | 1257 |
| LMArena Chinese | 1469 | 1262 |
| LMArena French | 1447 | 1286 |
| LMArena German | 1411 | 1273 |
| LMArena Japanese | 1378 | 1213 |
| LMArena Korean | 1337 | 1195 |
| LMArena Russian | 1405 | 1261 |
| LMArena Spanish | 1431 | 1279 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Grok 2 Mini 2024 08 13: 65.5 (#220)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1245 |
Long Context Grok 2 Mini 2024 08 13 leads
DeepSeek-V3.1: 36.3 (#232), Grok 2 Mini 2024 08 13: 38.4 (#196)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Longer Query | 1422 | 1266 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Grok 2 Mini 2024 08 13: 47.3 (#211)
| Benchmark | DeepSeek-V3.1 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Text | 1420 | 1281 |
| LMArena Creative Writing | 1401 | 1242 |
| LMArena Multi-Turn | 1408 | 1265 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Grok 2 Mini 2024 08 13?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.7 on the Noometry Index.
Is DeepSeek-V3.1 or Grok 2 Mini 2024 08 13 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 37.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Grok 2 Mini 2024 08 13 share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Grok 2 Mini 2024 08 13 has 17.