Model comparison
DeepSeek-V3.1 vs Grok-3 mini
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeekSummary
- They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 3 categories and Grok-3 mini in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 13.6.
- The biggest single-benchmark swing is Fiction.LiveBench: 52.8% for DeepSeek-V3.1 and 66.7% for Grok-3 mini.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Grok-3 mini | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 42.8 | 41.2 |
| Released | 2025-08-21 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1: 40.3 (#144), Grok-3 mini: 40.8 (#131)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| WeirdML | 38.4% | 42.6% |
| LMArena Coding | 1417 | 1379 |
| Aider Polyglot | — | 49.3% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Grok-3 mini: 13.6 (#334)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 61.3% |
| LMArena Hard Prompts | 1417 | 1375 |
| Epoch Capabilities Index | 139.92 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | 40% | — |
| ARC-AGI-1 | — | 16.5% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
Math Grok-3 mini leads
DeepSeek-V3.1: 38.9 (#122), Grok-3 mini: 42.1 (#85)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| LMArena Math | 1420 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
DeepSeek-V3.1: 43.7 (#90), Grok-3 mini: 46.4 (#81)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1405 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 67.5% |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Grok-3 mini: 48.1 (#145)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1400 | 1352 |
| LMArena Chinese | 1469 | 1387 |
| LMArena French | 1447 | 1357 |
| LMArena German | 1411 | 1349 |
| LMArena Japanese | 1378 | 1342 |
| LMArena Korean | 1337 | 1335 |
| LMArena Russian | 1405 | 1353 |
| LMArena Spanish | 1431 | 1381 |
Instruction Following Grok-3 mini leads
DeepSeek-V3.1: 73.9 (#110), Grok-3 mini: 78.5 (#9)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1400 | 1357 |
| IFEval | — | 95.1% |
Long Context Grok-3 mini leads
DeepSeek-V3.1: 36.3 (#232), Grok-3 mini: 41.0 (#147)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| Fiction.LiveBench | 52.8% | 66.7% |
| LMArena Longer Query | 1422 | 1372 |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Grok-3 mini: 52.5 (#169)
| Benchmark | DeepSeek-V3.1 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1420 | 1370 |
| LMArena Creative Writing | 1401 | 1342 |
| LMArena Multi-Turn | 1408 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1436 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is DeepSeek-V3.1 better than Grok-3 mini?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 41.2 on the Noometry Index.
Is DeepSeek-V3.1 or Grok-3 mini better for coding?
They score almost the same on coding (40.3 vs 40.8); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V3.1 and Grok-3 mini share?
21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Grok-3 mini has 35.