Model comparison
DeepSeek V4.1 Flash vs Grok-2 (Dec 2024)
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeekSummary
- They share 16 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 16.4.
- The biggest single-benchmark swing is DTBench: 89.9% for DeepSeek V4.1 Flash and 65.2% for Grok-2 (Dec 2024).
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 50.3 | 33.4 |
| Released | 2026-09-09 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 25 | 34 |
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: 52.8 (#29), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Coding | 1511 | 1288 |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 22.2% |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 1,092 | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 46.2 (#39), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1272 |
| DTBench | 89.9% | 65.2% |
| Epoch Capabilities Index | 155.01 | 130.48 |
| SimpleBench | — | 22.7% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| LiveBench | — | 54.3% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 48.4 (#52), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Math | 1493 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| ProofBench | 54% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 41.6 (#97), Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Expert | 1505 | 1254 |
| GPQA Diamond | — | 53.8% |
| Confabulations | — | 20.1% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.5 (#29), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1452 | 1282 |
| LMArena Chinese | 1506 | 1289 |
| LMArena French | 1448 | 1317 |
| LMArena Russian | 1473 | 1286 |
| LMArena Spanish | 1499 | 1281 |
| LMArena German | — | 1287 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1237 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.6 (#24), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1475 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#46), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1476 | 1276 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.8 (#43), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | DeepSeek V4.1 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1465 | 1305 |
| LMArena Creative Writing | 1436 | 1284 |
| LMArena Multi-Turn | 1460 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Grok-2 (Dec 2024)?
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index.
Is DeepSeek V4.1 Flash or Grok-2 (Dec 2024) better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 32.9 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Grok-2 (Dec 2024) share?
16 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Grok-2 (Dec 2024) has 34.