Grok 4.7 scores 49.8 on the Respan Index (#23), ahead of Qwen3.7-Max at 40.5 (#45). Grok 4.7 leads on 12 of the 16 benchmarks both report. Grok 4.7 is 1.3x cheaper per token at list price. Qwen3.7-Max has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 54% |
| 43.6% |
| LiveBench Coding (LiveBench) | 77.2% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 76.9% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 75.3% | 74% |
| LiveBench Language (LiveBench) | 80.1% | 79.7% |
| LiveBench Mathematics (LiveBench) | 95.7% | 85.2% |
| LiveBench Reasoning (LiveBench) | 82.7% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 29% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.1% | 95.6% |
| SimpleQA Verified | 56% | 55.8% |
| LMArena Agent (LMArena) | 0.0404 | -0.0513 |
| LMArena WebDev (LMArena) | 1638 | 1515 |
Higher is better. Each score links to where it was published.