Model comparison
DeepSeek-R1 vs Grok 4.7
Grok 4.7 is the stronger model overall, scoring 53.1 to 42.3 on the Noometry Index. DeepSeek-R1 costs 3.3× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. DeepSeek-R1 scores higher in 2 categories and Grok 4.7 in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.4% for DeepSeek-R1 and 98.1% for Grok 4.7.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 164K.
Side by side
| DeepSeek-R1 | Grok 4.7 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 42.3 | 53.1 |
| Released | 2025-01-20 | 2026-09-21 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 500K |
| Max output | 64K | 500K |
| Input $ / M tokens | $0.50 | $2 |
| Output $ / M tokens | $2.15 | $6 |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
DeepSeek-R1: 46.3 (#68), Grok 4.7: 58.0 (#18)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| SciCode | 35.7% | 57.8% |
| LMArena Coding | 1427 | 1427 |
| FrontierCode | — | 47.6% |
| Aider Polyglot | 71.4% | — |
| CursorBench | — | 46.3% |
| LMArena WebDev | — | 1639 |
| FrontierSWE | — | 29.5% |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Grok 4.7 leads
DeepSeek-R1: 30.7 (#75), Grok 4.7: 36.7 (#37)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| APEX-Agents | — | 54.6% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| GDP.pdf | — | 22.8% |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 10,537 |
Reasoning Grok 4.7 leads
DeepSeek-R1: 18.6 (#278), Grok 4.7: 49.1 (#40)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| CritPt | 1.1% | 18% |
| LMArena Hard Prompts | 1416 | 1413 |
| Epoch Capabilities Index | 141.29 | 153.53 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 76.8% |
| ARC-AGI-1 | 21.2% | — |
| Chess Puzzles | — | 38% |
| LiveBench Reasoning | 83.2% | — |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 96% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 49.4% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Grok 4.7 leads
DeepSeek-R1: 43.8 (#79), Grok 4.7: 57.8 (#39)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 98.1% |
| LMArena Math | 1400 | 1407 |
| FrontierMath (Tiers 1-3) | — | 53% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 34% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge Grok 4.7 leads
DeepSeek-R1: 44.5 (#87), Grok 4.7: 62.8 (#22)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 76.3% | 92.7% |
| LMArena Expert | 1394 | 1422 |
| SimpleQA Verified | — | 56% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Grok 4.7: 35.5 (#87)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| LMArena Vision | — | 1228 |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Grok 4.7: 50.8 (#116)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1412 | 1389 |
| LMArena Chinese | 1442 | 1455 |
| LMArena French | 1417 | 1455 |
| LMArena Russian | 1423 | 1397 |
| LMArena Spanish | 1411 | 1400 |
| LMArena German | 1404 | — |
| LMArena Japanese | 1391 | — |
| LMArena Korean | 1360 | — |
Instruction Following Grok 4.7 leads
DeepSeek-R1: 72.0 (#143), Grok 4.7: 74.1 (#105)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1404 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Grok 4.7: 43.1 (#104)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1391 | 1413 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Grok 4.7 leads
DeepSeek-R1: 61.4 (#88), Grok 4.7: 70.0 (#24)
| Benchmark | DeepSeek-R1 | Grok 4.7 |
|---|---|---|
| LMArena Text | 1428 | 1399 |
| LMArena Creative Writing | 1405 | 1391 |
| EQ-Bench Creative Writing | 1500 | 2007 |
| LMArena Multi-Turn | 1405 | 1393 |
| Short-Story Creative Writing | 83% | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Grok 4.7?
Grok 4.7 is the stronger model overall, scoring 53.1 to 42.3 on the Noometry Index. DeepSeek-R1 costs 3.3× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Grok 4.7?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Grok 4.7 lists at $2 and $6.
Is DeepSeek-R1 or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 46.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 164K.
How many benchmarks do DeepSeek-R1 and Grok 4.7 share?
20 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Grok 4.7 has 39.