Gemini 3.7 Flash scores 48.6 on the Respan Index (#26), ahead of Qwen3.7-Max at 40.5 (#45). Gemini 3.7 Flash leads on 15 of the 16 benchmarks both report. Gemini 3.7 Flash is 2.5x cheaper per token at list price. Gemini 3.7 Flash has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| 58.3% |
| 43.6% |
| LiveBench Coding (LiveBench) | 78.9% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 68% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 79.9% | 74% |
| LiveBench Language (LiveBench) | 85.5% | 79.7% |
| LiveBench Mathematics (LiveBench) | 93.5% | 85.2% |
| LiveBench Reasoning (LiveBench) | 87.8% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 37% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 97.2% | 95.6% |
| SimpleQA Verified | 69.2% | 55.8% |
| LMArena Agent (LMArena) | -0.0149 | -0.0513 |
| LMArena WebDev (LMArena) | 1592 | 1515 |
Higher is better. Each score links to where it was published.