Gemini 3.7 Flash scores 48.6 on the Respan Index (#26), ahead of DeepSeek V4 Flash at 43.3 (#37). Gemini 3.7 Flash leads on 16 of the 18 benchmarks both report. Gemini 3.7 Flash has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| GPQA Diamond |
| 91% |
| 94.8% |
| LiveBench Agentic Coding (LiveBench) | 46.8% | 58.3% |
| LiveBench Coding (LiveBench) | 75% | 78.9% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 68% |
| LiveBench Instruction Following (LiveBench) | 65.5% | 79.9% |
| LiveBench Language (LiveBench) | 79.2% | 85.5% |
| LiveBench Mathematics (LiveBench) | 86.8% | 93.5% |
| LiveBench Reasoning (LiveBench) | 86.6% | 87.8% |
| Mystery Game Puzzles (Epoch AI) | 34% | 37% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.4% | 97.2% |
| SimpleQA Verified | 33.6% | 69.2% |
| Terminal-Bench 4.0 (Vals AI) | 18.7% | 12.1% |
| LMArena Elo | 1436 | 1488 |
| LMArena WebDev (LMArena) | 1581 | 1592 |
Higher is better. Each score links to where it was published.