Gemini 3.6 Flash vs Gemini 3.7 Flash
| Spec | Gemini 3.6 Flash | Gemini 3.7 Flash |
|---|---|---|
| Respan Index | 45.6 (#54) | 52.0 (#40) |
| Blended price per 1M | $1.5 | $1.5 |
| Context window | 1.0M | 1.0M |
| Input / output per 1M | $0.75 / $3.75 | $0.75 / $3.75 |
| Max output | 66K | 66K |
| Input | text, vision, audio | text, vision, audio |
| Released | 2026-07-21 | 2026-08-13 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Gemini 3.6 Flash | Gemini 3.7 Flash |
|---|---|---|
| Coding | 22.3 Gemini 3.6 Flash | 32.4 Gemini 3.7 Flash |
| Agents | 58.4 Gemini 3.6 Flash | 66.0 Gemini 3.7 Flash |
| Reasoning | 42.6 Gemini 3.6 Flash | 48.2 Gemini 3.7 Flash |
| Knowledge & language | 65.3 Gemini 3.6 Flash | 69.2 Gemini 3.7 Flash |
| Human preference | 54.7 Gemini 3.6 Flash | 56.1 Gemini 3.7 Flash |
Benchmarks both report
Gemini 3.7 Flash leads on 26 of the 26 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Gemini 3.6 Flash | Gemini 3.7 Flash |
|---|---|---|
| LMArena Elo | 1483 | 1490 |
| LMArena Vision (LMArena) | 1280 | 1294 |
| LMArena WebDev (LMArena) | 1538 | 1589 |
| MirrorCode (Epoch AI) | 23.3% | 41.1% |
| Chess Puzzles (Epoch AI) | 42% | 66% |
| LMArena Agent (LMArena) | -0.0445 | -0.0307 |
| APEX-Agents (Mercor) | 46.9% | 67.8% |
| DeepSWE v1.1 (Datacurve) | 46.7% | 65.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 22% | 36.6% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 58.9% | 71.6% |
| Furniture Assembly (Epoch AI) | 23.3% | 26.7% |
| GPQA Diamond | 94.1% | 94.8% |
| LiveBench Agentic Coding (LiveBench) | 43.4% | 58.3% |
| LiveBench Coding (LiveBench) | 77.9% | 78.9% |
| LiveBench Data Analysis (LiveBench) | 63% | 68% |
| LiveBench Instruction Following (LiveBench) | 75.4% | 79.9% |
| LiveBench Language (LiveBench) | 83.9% | 85.5% |
| LiveBench Mathematics (LiveBench) | 86.4% | 93.5% |
| LiveBench Reasoning (LiveBench) | 85.1% | 87.8% |
| Mystery Game Puzzles (Epoch AI) | 30% | 37% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 94.2% | 97.2% |
| SAGE (Vals AI) | 48.7% | 49.2% |
| SimpleQA Verified | 66.2% | 69.2% |
| DeepSWE v1.1 | 49% | 65.3% |
| GDPVal-AA v2 | 1421 | 1525 |
| Terminal-bench 2.1 | 78% | 85.8% |
FAQ
Is Gemini 3.6 Flash better than Gemini 3.7 Flash?
Gemini 3.7 Flash scores 52.0 on the Respan Index (#40), ahead of Gemini 3.6 Flash at 45.6 (#54). Gemini 3.7 Flash leads on 26 of the 26 benchmarks both report.
Which is cheaper, Gemini 3.6 Flash or Gemini 3.7 Flash?
Gemini 3.6 Flash lists at $0.75 input and $3.75 output per 1M tokens; Gemini 3.7 Flash at $0.75 and $3.75. Both cost about the same per token at list price.
Which has the larger context window?
Both accept 1.0M tokens of context.
Compare other models
- vsGemini 3.6 Flash vs Gemini 3.5 Flash
- vsGemini 3.8 Flash vs Gemini 3.7 Flash
- vsGemini 3.8 Flash vs Gemini 3.6 Flash
- vsClaude Sonnet 5.5 vs Gemini 3.6 Flash
- vsGemini 3.6 Flash vs Muse Spark 1.2
- vsGemini 3.6 Flash vs GLM-5.3-Flash
- vsGemini 3.6 Flash vs Grok 4.5
- vsGemini 3.7 Flash vs GLM-5.3
- vsGemini 3.7 Flash vs MiMo-V2.6-Flash
- vsGemini 3.7 Flash vs MiniMax M3.1 Flash