Model comparison
DeepSeek-V3 vs Grok 4.1 Fast
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 39.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. DeepSeek-V3 scores higher in 5 categories and Grok 4.1 Fast in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 43.4 to 20.5.
- The biggest single-benchmark swing is SimpleBench: 27.2% for DeepSeek-V3 and 56% for Grok 4.1 Fast.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.24 / $0.90 for DeepSeek-V3.
- DeepSeek-V3 accepts more context: 164K tokens versus 128K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | Grok 4.1 Fast | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 39.5 | 41.4 |
| Released | 2024-12-26 | 2025-06-27 |
| Weights | Open | Proprietary |
| Context window | 164K | 128K |
| Max output | 164K | 30K |
| Input $ / M tokens | $0.24 | $0.20 |
| Output $ / M tokens | $0.90 | $0.50 |
| Results tracked | 60 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 42.3 (#106), Grok 4.1 Fast: 34.1 (#245)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Coding | 1368 | 1411 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1242 |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| ALE-Bench | — | 394.93 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Grok 4.1 Fast: 36.3 (#39)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 69.6% |
| τ²-bench Banking | — | 13.1% |
| LMArena Search | — | 1171 |
| METR Time Horizons | 49.6% | — |
| Vending-Bench 2 | — | 1,107 |
Reasoning Grok 4.1 Fast leads
DeepSeek-V3: 20.5 (#236), Grok 4.1 Fast: 43.4 (#49)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| SimpleBench | 27.2% | 56% |
| LMArena Hard Prompts | 1365 | 1407 |
| DTBench | 64.8% | 87.7% |
| ForecastBench | 59.1 | 61 |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 87.4% |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Too close to call
DeepSeek-V3: 32.1 (#219), Grok 4.1 Fast: 31.9 (#221)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Math | 1373 | 1408 |
| MathArena Final-Answer Competitions | — | 60.9% |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 4% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge DeepSeek-V3 leads
DeepSeek-V3: 37.5 (#155), Grok 4.1 Fast: 33.1 (#207)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| Vectara Hallucination Rate | 6.1% | 17.8% |
| LMArena Expert | 1351 | 1399 |
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multimodal Not comparable
DeepSeek-V3: —, Grok 4.1 Fast: 37.0 (#76)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Vision | — | 1201 |
Multilingual Grok 4.1 Fast leads
DeepSeek-V3: 48.5 (#143), Grok 4.1 Fast: 51.0 (#114)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Non-English | 1358 | 1391 |
| LMArena Chinese | 1391 | 1441 |
| LMArena French | 1385 | 1415 |
| LMArena German | 1374 | 1404 |
| LMArena Japanese | 1333 | 1349 |
| LMArena Korean | 1319 | 1361 |
| LMArena Russian | 1373 | 1387 |
| LMArena Spanish | 1358 | 1413 |
Instruction Following Too close to call
DeepSeek-V3: 72.8 (#130), Grok 4.1 Fast: 72.7 (#133)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Instruction Following | 1345 | 1376 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Grok 4.1 Fast leads
DeepSeek-V3: 34.0 (#253), Grok 4.1 Fast: 42.4 (#126)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Longer Query | 1352 | 1390 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Too close to call
DeepSeek-V3: 57.4 (#130), Grok 4.1 Fast: 57.2 (#131)
| Benchmark | DeepSeek-V3 | Grok 4.1 Fast |
|---|---|---|
| LMArena Text | 1375 | 1408 |
| LMArena Creative Writing | 1364 | 1394 |
| EQ-Bench Creative Writing | 1472 | 1327 |
| LMArena Multi-Turn | 1389 | 1389 |
| Short-Story Creative Writing | 77% | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Grok 4.1 Fast?
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 39.5 on the Noometry Index.
Which is cheaper, DeepSeek-V3 or Grok 4.1 Fast?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; DeepSeek-V3 lists at $0.24 and $0.90.
Is DeepSeek-V3 or Grok 4.1 Fast better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3 does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3 and Grok 4.1 Fast share?
22 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Grok 4.1 Fast has 32.