Model comparison
DeepSeek V4.1 Flash vs Grok 4
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 48.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeekSummary
- They share 21 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 7 categories and Grok 4 in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 48.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 84% for Grok 4.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Grok 4 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 52.8 | 48.1 |
| Released | 2026-09-09 | 2025-07-09 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Grok 4: 50.3 (#46)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Coding | 1506 | 1408 |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 45.7% |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use Grok 4 leads
DeepSeek V4.1 Flash: 31.2 (#69), Grok 4: 32.3 (#68)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 39.5% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| GDP.pdf | 19.8% | — |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Grok 4: 36.7 (#65)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1409 |
| Epoch Capabilities Index | 154.9 | 146.44 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 66.7% |
| CritPt | 14.3% | — |
| Chess Puzzles | — | 28% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 60.9 |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Grok 4: 48.4 (#64)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 84% |
| LMArena Math | 1477 | 1422 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 60.3% |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Grok 4: 53.8 (#55)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| GPQA Diamond | 89.8% | 87% |
| LMArena Expert | 1506 | 1415 |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), Grok 4: 33.7 (#94)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Vision | 1277 | 1210 |
| GeoBench | — | 45% |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Grok 4: 51.8 (#103)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Non-English | 1448 | 1403 |
| LMArena Chinese | 1497 | 1427 |
| LMArena French | 1452 | 1418 |
| LMArena German | 1484 | 1429 |
| LMArena Japanese | 1412 | 1394 |
| LMArena Korean | 1452 | 1377 |
| LMArena Russian | 1471 | 1410 |
| LMArena Spanish | 1459 | 1420 |
Instruction Following Grok 4 leads
DeepSeek V4.1 Flash: 77.3 (#26), Grok 4: 79.2 (#5)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1387 |
| IFEval | — | 94.9% |
Long Context Grok 4 leads
DeepSeek V4.1 Flash: 45.2 (#47), Grok 4: 63.1 (#4)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1475 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Grok 4: 58.5 (#116)
| Benchmark | DeepSeek V4.1 Flash | Grok 4 |
|---|---|---|
| LMArena Text | 1462 | 1411 |
| LMArena Creative Writing | 1435 | 1397 |
| LMArena Multi-Turn | 1457 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench Creative Writing | 1540 | — |
| WildBench | — | 79.7% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Grok 4?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 48.1 on the Noometry Index.
Is DeepSeek V4.1 Flash or Grok 4 better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 50.3 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Grok 4 share?
21 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Grok 4 has 48.