Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Grok 4 Fast
Grok 4 Fast has enough public results to be ranked (#167); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Grok 4 Fast in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 32.5.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 40.3 | 39.4 |
| Released | 2024-05-07 | 2025-09-19 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Grok 4 Fast: 32.5 (#271)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| LMArena WebDev | — | 1159 |
| WeirdML | — | 42.9% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1429 |
| BigCodeBench Complete | 59.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 29.5 (#86)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 22.2 (#201)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 144.2 |
| ARC-AGI-2 | — | 5.3% |
| Kagi LLM Benchmark | — | 66.1% |
| ARC-AGI-1 | — | 48.5% |
| LMArena Hard Prompts | — | 1412 |
| DTBench | — | 82.7% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 60.5 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 38.9 (#123)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| LMArena Math | — | 1419 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 32.0 (#214)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| Vectara Hallucination Rate | — | 19.7% |
| LMArena Expert | — | 1411 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 51.3 (#111)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | — | 1396 |
| LMArena Chinese | — | 1457 |
| LMArena French | — | 1431 |
| LMArena German | — | 1383 |
| LMArena Japanese | — | 1352 |
| LMArena Korean | — | 1357 |
| LMArena Russian | — | 1389 |
| LMArena Spanish | — | 1415 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 73.2 (#121)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | — | 1387 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 63.2 (#3)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| Fiction.LiveBench | — | 94.4% |
| LMArena Longer Query | — | 1415 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Grok 4 Fast: 60.0 (#102)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Grok 4 Fast |
|---|---|---|
| LMArena Text | — | 1407 |
| LMArena Creative Writing | — | 1387 |
| LMArena Multi-Turn | — | 1414 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Grok 4 Fast?
Grok 4 Fast has enough public results to be ranked (#167); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Grok 4 Fast better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 32.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Grok 4 Fast share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Grok 4 Fast has 30.