Grok 4.7 scores 49.8 on the Respan Index (#23), ahead of DeepSeek V4 Flash at 43.3 (#37). Grok 4.7 leads on 12 of the 17 benchmarks both report. DeepSeek V4 Flash has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 46.8% |
| 54% |
| LiveBench Coding (LiveBench) | 75% | 77.2% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 76.9% |
| LiveBench Instruction Following (LiveBench) | 65.5% | 75.3% |
| LiveBench Language (LiveBench) | 79.2% | 80.1% |
| LiveBench Mathematics (LiveBench) | 86.8% | 95.7% |
| LiveBench Reasoning (LiveBench) | 86.6% | 82.7% |
| Mystery Game Puzzles (Epoch AI) | 34% | 29% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.4% | 98.1% |
| SimpleQA Verified | 33.6% | 56% |
| Terminal-Bench 4.0 (Vals AI) | 18.7% | 28.8% |
| LMArena Elo | 1436 | 1443 |
| LMArena WebDev (LMArena) | 1581 | 1638 |
Higher is better. Each score links to where it was published.