Model comparison
DeepSeek-V2.5 (Sep 2024) vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 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 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 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 4.6 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 37.6 | 56.9 |
| Released | 2024-09-06 | 2026-08-12 |
| Weights | Open | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 22 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Grok 4.6: 58.5 (#16)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Coding | 1309 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| Aider Polyglot | 17.8% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.6: 39.4 (#27)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Grok 4.6: 61.4 (#20)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1447 |
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.44 |
Math Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Grok 4.6: 67.0 (#24)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Math | 1288 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
Knowledge Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Grok 4.6: 63.3 (#20)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Expert | 1266 | 1467 |
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Grok 4.6: 43.6 (#23)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Grok 4.6: 53.0 (#74)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1273 | 1420 |
| LMArena Chinese | 1318 | 1480 |
| LMArena French | 1289 | 1461 |
| LMArena German | 1258 | 1431 |
| LMArena Japanese | 1228 | 1376 |
| LMArena Korean | 1209 | 1397 |
| LMArena Russian | 1289 | 1422 |
| LMArena Spanish | 1248 | 1404 |
Instruction Following Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Grok 4.6: 75.4 (#63)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1431 |
Long Context Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Grok 4.6: 44.5 (#66)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1301 | 1454 |
Writing & Preference Grok 4.6 leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Grok 4.6: 62.3 (#80)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Grok 4.6 |
|---|---|---|
| LMArena Text | 1294 | 1428 |
| LMArena Creative Writing | 1285 | 1428 |
| LMArena Multi-Turn | 1297 | 1425 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Grok 4.6 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Grok 4.6 has 49.