Model comparison
DeepSeek-V2.5 (Sep 2024) vs Grok 4.1 Fast
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 2 categories and Grok 4.1 Fast in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 43.4 to 25.6.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 37.6 | 41.4 |
| Released | 2024-09-06 | 2025-06-27 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 30K |
| Input $ / M tokens | — | $0.20 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Grok 4.1 Fast: 34.1 (#245)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Coding | 1309 | 1411 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1242 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 394.93 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.1 Fast: 36.3 (#39)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 69.6% |
| τ²-bench Banking | — | 13.1% |
| LMArena Search | — | 1171 |
| Vending-Bench 2 | — | 1,107 |
Reasoning Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Grok 4.1 Fast: 43.4 (#49)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1407 |
| SimpleBench | — | 56% |
| NYT Connections (extended) | — | 87.4% |
| DTBench | — | 87.7% |
| ForecastBench | — | 61 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Grok 4.1 Fast: 31.9 (#221)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Math | 1288 | 1408 |
| MathArena Final-Answer Competitions | — | 60.9% |
| ProofBench | — | 4% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Grok 4.1 Fast: 33.1 (#207)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Expert | 1266 | 1399 |
| Vectara Hallucination Rate | — | 17.8% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.1 Fast: 37.0 (#76)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Vision | — | 1201 |
Multilingual Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Grok 4.1 Fast: 51.0 (#114)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Non-English | 1273 | 1391 |
| LMArena Chinese | 1318 | 1441 |
| LMArena French | 1289 | 1415 |
| LMArena German | 1258 | 1404 |
| LMArena Japanese | 1228 | 1349 |
| LMArena Korean | 1209 | 1361 |
| LMArena Russian | 1289 | 1387 |
| LMArena Spanish | 1248 | 1413 |
Instruction Following Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Grok 4.1 Fast: 72.7 (#133)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Instruction Following | 1280 | 1376 |
Long Context Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Grok 4.1 Fast: 42.4 (#126)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Longer Query | 1301 | 1390 |
Writing & Preference Grok 4.1 Fast leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Grok 4.1 Fast: 57.2 (#131)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.1 Fast |
|---|---|---|
| LMArena Text | 1294 | 1408 |
| LMArena Creative Writing | 1285 | 1394 |
| LMArena Multi-Turn | 1297 | 1389 |
| EQ-Bench Creative Writing | — | 1327 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Grok 4.1 Fast?
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Grok 4.1 Fast better for coding?
Grok 4.1 Fast scores higher on coding benchmarks: 34.1 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Grok 4.1 Fast share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Grok 4.1 Fast has 32.