Model comparison
DeepSeek V4 Flash vs Grok 2 Mini 2024 08 13
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Grok 2 Mini 2024 08 13 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 23.7.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 53.6 | 37.0 |
| Released | 2026-04-24 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.6 (#56), Grok 2 Mini 2024 08 13: 36.4 (#194)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Coding | 1457 | 1269 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#25), Grok 2 Mini 2024 08 13: 23.7 (#162)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1255 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.51 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.0 (#31), Grok 2 Mini 2024 08 13: 32.8 (#185)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Math | 1427 | 1265 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.5 (#43), Grok 2 Mini 2024 08 13: 33.4 (#195)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Expert | 1441 | 1238 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.2 (#71), Grok 2 Mini 2024 08 13: 41.6 (#203)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Non-English | 1420 | 1257 |
| LMArena Chinese | 1467 | 1262 |
| LMArena French | 1438 | 1285 |
| LMArena German | 1418 | 1273 |
| LMArena Japanese | 1403 | 1213 |
| LMArena Korean | 1383 | 1195 |
| LMArena Russian | 1428 | 1261 |
| LMArena Spanish | 1437 | 1278 |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 75.1 (#76), Grok 2 Mini 2024 08 13: 65.7 (#215)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1245 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#81), Grok 2 Mini 2024 08 13: 38.4 (#191)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Longer Query | 1435 | 1267 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 64.0 (#59), Grok 2 Mini 2024 08 13: 47.5 (#207)
| Benchmark | DeepSeek V4 Flash | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Text | 1432 | 1281 |
| LMArena Creative Writing | 1403 | 1242 |
| LMArena Multi-Turn | 1449 | 1265 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Grok 2 Mini 2024 08 13?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.0 on the Noometry Index.
Is DeepSeek V4 Flash or Grok 2 Mini 2024 08 13 better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 36.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Grok 2 Mini 2024 08 13 share?
17 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Grok 2 Mini 2024 08 13 has 17.