DeepSeek V4.1 Flash vs Gemini 3.8 Flash
| Spec | DeepSeek V4.1 Flash | Gemini 3.8 Flash |
|---|---|---|
| Respan Index | 52.5 (#37) | 54.5 (#31) |
| Blended price per 1M | $0.089 | $1.5 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $0.051 / $0.203 | $0.75 / $3.75 |
| Max output | 384K | 66K |
| Input | text, vision | text, vision, audio |
| Released | 2026-09-10 | 2026-09-02 |
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 | DeepSeek V4.1 Flash | Gemini 3.8 Flash |
|---|---|---|
| Coding | 43.7 DeepSeek V4.1 Flash | 36.1 Gemini 3.8 Flash |
| Agents | 58.4 DeepSeek V4.1 Flash | 66.7 Gemini 3.8 Flash |
| Reasoning | 55.5 DeepSeek V4.1 Flash | 53.4 Gemini 3.8 Flash |
| Knowledge & language | 44.5 DeepSeek V4.1 Flash | 70.9 Gemini 3.8 Flash |
| Human preference | 57.5 DeepSeek V4.1 Flash | 56.0 Gemini 3.8 Flash |
Benchmarks both report
Gemini 3.8 Flash leads on 15 of the 26 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.8 Flash |
|---|---|---|
| LMArena Elo | 1475 | 1497 |
| LMArena Vision (LMArena) | 1262 | 1293 |
| LMArena WebDev (LMArena) | 1659 | 1584 |
| LMArena Agent (LMArena) | 0.0078 | 0.0149 |
| MirrorCode (Epoch AI) | 64.4% | 38.9% |
| APEX-Agents (Mercor) | 39.5% | 64.3% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 22% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 67.4% | 68.4% |
| GPQA Diamond | 90.9% | 95.4% |
| Mystery Game Puzzles (Epoch AI) | 43% | 47% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.3% | 98.9% |
| Terminal-Bench 4.0 (Vals AI) | 19.7% | 19.7% |
| SAGE 1.1 (Vals AI) | 85.4% | 88.2% |
| Chess Puzzles (Epoch AI) | 48% | 58% |
| SimpleQA Verified | 42.9% | 69.7% |
| Furniture Assembly (Epoch AI) | 34.2% | 31.7% |
| LiveBench Agentic Coding (LiveBench) | 77.3% | 54.2% |
| LiveBench Coding (LiveBench) | 80% | 72.5% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 54% |
| LiveBench Instruction Following (LiveBench) | 70% | 81.4% |
| LiveBench Language (LiveBench) | 81.2% | 87.8% |
| LiveBench Mathematics (LiveBench) | 93.3% | 91.6% |
| LiveBench Reasoning (LiveBench) | 86.7% | 89.3% |
| SAGE (Vals AI) | 47.9% | 35.1% |
| SimpleBench (SimpleBench) | 66.7% | 82.4% |
| DeepSWE v1.1 | 74.2% | 73.7% |
FAQ
Is DeepSeek V4.1 Flash better than Gemini 3.8 Flash?
Gemini 3.8 Flash scores 54.5 on the Respan Index (#31), ahead of DeepSeek V4.1 Flash at 52.5 (#37). Gemini 3.8 Flash leads on 15 of the 26 benchmarks both report.
Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.8 Flash?
DeepSeek V4.1 Flash lists at $0.051 input and $0.203 output per 1M tokens; Gemini 3.8 Flash at $0.75 and $3.75. DeepSeek V4.1 Flash is 17x cheaper per token at list price.
Which has the larger context window?
DeepSeek V4.1 Flash accepts 1M tokens and Gemini 3.8 Flash 1.0M tokens.
Compare other models
- vsDeepSeek V4.1 Flash vs DeepSeek V4 Flash
- vsGemini 3.8 Flash vs Gemini 3.7 Flash
- vsClaude Sonnet 5.5 vs Gemini 3.8 Flash
- vsGemini 3.8 Flash vs Claude Sonnet 5
- vsDeepSeek V4.1 Flash vs Qwen3.8-Max
- vsDeepSeek V4.1 Flash vs MiniMax M3.1 Flash
- vsDeepSeek V4.1 Flash vs Kimi K3
- vsGemini 3.8 Flash vs GPT-5.5
- vsGemini 3.8 Flash vs Grok 4.6
- vsGemini 3.8 Flash vs GPT-5.6 Terra