Model comparison
DeepSeek LLM 67B vs Grok 4 Fast
Grok 4 Fast is the stronger model overall, scoring 39.4 to 24.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4 Fast in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 Fast leads 38.9 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Grok 4 Fast | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 24.9 | 39.4 |
| Released | 2023-11-29 | 2025-09-19 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek LLM 67B: 31.9 (#278), Grok 4 Fast: 32.5 (#271)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Coding | 1096 | 1429 |
| LMArena WebDev | — | 1159 |
| WeirdML | — | 42.9% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Grok 4 Fast: 29.5 (#86)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |
Reasoning Grok 4 Fast leads
DeepSeek LLM 67B: 16.5 (#304), Grok 4 Fast: 22.2 (#201)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1412 |
| Epoch Capabilities Index | 110.5 | 144.2 |
| ARC-AGI-2 | — | 5.3% |
| Kagi LLM Benchmark | — | 66.1% |
| ARC-AGI-1 | — | 48.5% |
| Chess Puzzles | 0% | — |
| DTBench | — | 82.7% |
| ForecastBench | — | 60.5 |
Math Grok 4 Fast leads
DeepSeek LLM 67B: 8.7 (#324), Grok 4 Fast: 38.9 (#123)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1108 | 1419 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Grok 4 Fast leads
DeepSeek LLM 67B: 7.0 (#313), Grok 4 Fast: 32.0 (#214)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 19.7% |
| LMArena Expert | — | 1411 |
Multilingual Grok 4 Fast leads
DeepSeek LLM 67B: 29.4 (#267), Grok 4 Fast: 51.3 (#111)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1073 | 1396 |
| LMArena Chinese | 1132 | 1457 |
| LMArena French | — | 1431 |
| LMArena German | — | 1383 |
| LMArena Japanese | — | 1352 |
| LMArena Korean | — | 1357 |
| LMArena Russian | — | 1389 |
| LMArena Spanish | — | 1415 |
Instruction Following Grok 4 Fast leads
DeepSeek LLM 67B: 55.4 (#277), Grok 4 Fast: 73.2 (#121)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1079 | 1387 |
Long Context Grok 4 Fast leads
DeepSeek LLM 67B: 33.1 (#265), Grok 4 Fast: 63.2 (#3)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1092 | 1415 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 Fast leads
DeepSeek LLM 67B: 31.6 (#282), Grok 4 Fast: 60.0 (#102)
| Benchmark | DeepSeek LLM 67B | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1105 | 1407 |
| LMArena Creative Writing | 1067 | 1387 |
| LMArena Multi-Turn | 1082 | 1414 |
Frequently asked questions
Is DeepSeek LLM 67B better than Grok 4 Fast?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Grok 4 Fast better for coding?
They score almost the same on coding (31.9 vs 32.5); test both on your own repository before choosing.
How many benchmarks do DeepSeek LLM 67B and Grok 4 Fast share?
11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4 Fast has 30.