Model comparison
DeepSeek V4 Flash vs Grok-2 (Dec 2024)
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 33.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeekSummary
- They share 23 benchmarks with published results for both. DeepSeek V4 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 math, where DeepSeek V4 Flash leads 60.3 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for DeepSeek V4 Flash and 11.5% for Grok-2 (Dec 2024).
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Flash | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 53.6 | 33.7 |
| 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 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 63% | 22.2% |
| LMArena Coding | 1457 | 1287 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 61.1% | 22.7% |
| LMArena Hard Prompts | 1444 | 1272 |
| DTBench | 90.9% | 65.2% |
| Epoch Capabilities Index | 154.49 | 130.48 |
| ARC-AGI-2 | 61.4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| LiveBench Reasoning | — | 54.8% |
| Mystery Game Puzzles | 34% | — |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 41.7% | — |
| LiveBench | — | 54.3% |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 11.5% |
| LMArena Math | 1427 | 1283 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 91% | 53.8% |
| LMArena Expert | 1441 | 1254 |
| SimpleQA Verified | 33.6% | — |
| Confabulations | — | 20.1% |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1420 | 1282 |
| LMArena Chinese | 1468 | 1289 |
| LMArena French | 1439 | 1318 |
| LMArena German | 1418 | 1287 |
| LMArena Japanese | 1406 | 1244 |
| LMArena Korean | 1384 | 1237 |
| LMArena Russian | 1428 | 1286 |
| LMArena Spanish | 1436 | 1281 |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1421 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1434 | 1276 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | DeepSeek V4 Flash | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1432 | 1305 |
| LMArena Creative Writing | 1403 | 1284 |
| LMArena Multi-Turn | 1449 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1559 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is DeepSeek V4 Flash better than Grok-2 (Dec 2024)?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 33.7 on the Noometry Index.
Is DeepSeek V4 Flash or Grok-2 (Dec 2024) better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 33.3 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Grok-2 (Dec 2024) share?
23 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Grok-2 (Dec 2024) has 34.