Gemini 3.7 Flash scores 48.6 on the Respan Index (#26), ahead of Kimi K2.7 Code at 34.1 (#58). Gemini 3.7 Flash leads on 16 of the 16 benchmarks both report. Gemini 3.7 Flash is 1.1x 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
| FrontierMath Tiers 1-3 v2 (Epoch AI) |
| 71.6% |
| 54% |
| GPQA Diamond | 94.8% | 87.9% |
| LiveBench Agentic Coding (LiveBench) | 58.3% | 45.7% |
| LiveBench Coding (LiveBench) | 78.9% | 74% |
| LiveBench Data Analysis (LiveBench) | 68% | 62.7% |
| LiveBench Instruction Following (LiveBench) | 79.9% | 56.3% |
| LiveBench Language (LiveBench) | 85.5% | 77.9% |
| LiveBench Mathematics (LiveBench) | 93.5% | 79.6% |
| LiveBench Reasoning (LiveBench) | 87.8% | 82.8% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 97.2% | 95.6% |
| SimpleQA Verified | 69.2% | 36.5% |
| LMArena WebDev (LMArena) | 1592 | 1473 |
Higher is better. Each score links to where it was published.