DeepSeek V4 Pro vs Gemini 4 Neon
| Spec | DeepSeek V4 Pro | Gemini 4 Neon |
|---|---|---|
| Respan Index | 49.2 (#45) | 78.2 (#2) |
| Blended price per 1M | $0.585 | $6 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.28 / $1.5 | $3 / $15 |
| Max output | 384K | 66K |
| Input | text | text, image, audio, video |
| Released | 2026-08-13 | 2026-11-18 |
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 Pro | Gemini 4 Neon |
|---|---|---|
| Coding | 29.8 DeepSeek V4 Pro | 74.1 Gemini 4 Neon |
| Agents | 59.7 DeepSeek V4 Pro | 84.5 Gemini 4 Neon |
| Reasoning | 52.8 DeepSeek V4 Pro | 87.8 Gemini 4 Neon |
| Knowledge & language | 52.6 DeepSeek V4 Pro | 75.3 Gemini 4 Neon |
| Human preference | 55.6 DeepSeek V4 Pro | 60.4 Gemini 4 Neon |
Benchmarks both report
Gemini 4 Neon leads on 13 of the 13 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek V4 Pro | Gemini 4 Neon |
|---|---|---|
| LMArena WebDev (LMArena) | 1581 | 1765 |
| LMArena Elo | 1464 | 1513 |
| LMArena Agent (LMArena) | -0.003 | 0.1841 |
| Chess Puzzles (Epoch AI) | 46% | 83% |
| APEX-Agents (Mercor) | 47.3% | 82.9% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 97.6% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 64.6% | 91.2% |
| GPQA Diamond | 91.7% | 96.3% |
| Mystery Game Puzzles (Epoch AI) | 43% | 85% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.6% | 100% |
| SimpleQA Verified | 52.9% | 75.2% |
| Vending-Bench 2 (Andon Labs) | 3284.52 | 16843.41 |
| SimpleBench (SimpleBench) | 50.9% | 94.4% |
FAQ
Is DeepSeek V4 Pro better than Gemini 4 Neon?
Gemini 4 Neon scores 78.2 on the Respan Index (#2), ahead of DeepSeek V4 Pro at 49.2 (#45). Gemini 4 Neon leads on 13 of the 13 benchmarks both report.
Which is cheaper, DeepSeek V4 Pro or Gemini 4 Neon?
DeepSeek V4 Pro lists at $0.28 input and $1.5 output per 1M tokens; Gemini 4 Neon at $3 and $15. DeepSeek V4 Pro is 10x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.