🔥 DeepSeek V4 Official Leaked: Outperforms Claude Opus 4.8
DeepSeek V4 official hasn't been formally announced yet, but the API has already silently switched to the official version via gray release. Multiple independent testers have run deep evaluations with a stunning conclusion: V4 outperforms Claude Opus 4.8, generating complete, playable 3D games from a single text prompt.
Based on independent tester feedback, DeepSeek V4 official's overall capability surpasses Claude Opus 4.8, placing it between Opus 4.8 and Gemini 2.5 Pro. This makes DeepSeek the third provider globally to achieve "super-Opus" capability — at 1/50th the price of Opus.
📊 V4 Official vs Global Top Models
| Model | Overall | Code Gen | Price (Output/M tokens) | Status |
|---|---|---|---|---|
| Claude Opus 4.8 | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | $75 | Released |
| DeepSeek V4 Official | ⭐⭐⭐⭐☆ | ⭐⭐⭐⭐⭐ | ~$0.83 (off-peak $0.42) | Gray release |
| Gemini 2.5 Pro | ⭐⭐⭐⭐☆ | ⭐⭐⭐⭐ | $10 | Released |
| GPT-4o | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | $10 | Released |
| Grok 4 | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | $15 | Released |
Bottom line: DeepSeek V4 outperforms Opus 4.8 at 1/90th the price (off-peak) to 1/45th (peak). This is currently the world's highest value frontier model.
🎮 Real-World Evidence: One Prompt = Complete Game
Here are 10 independent Bilibili creator tests using DeepSeek V4 official (gray release), generating complete, runnable games from a single text prompt:
① Terraria / Binding of Isaac / RTS / Cut the Rope / Stardew Valley
Multi-genre generalization test covering 6 different game types. V4 performed stunningly.
② Three Game Examples from Single Prompts
Three different game styles from single prompts, testing consistency and reliability.
③ Backrooms & Horror Game from One Prompt
Backrooms-style horror game with atmosphere, jump scares, and level design.
④ Minecraft Clone 🔥
The most impactful test: a complete 3D voxel game with block placement, destruction, and inventory systems. Core evidence for the "outperforms Opus 4.8" claim.
⑤ CS:GO-Style FPS
FPS game from one prompt, including shooting, movement, and map design.
⑥ Comparison: Gemini 3.5 Pro / Grok 4.5
Head-to-head comparison of V4 vs Gemini and Grok in code generation tasks.
⑦ Super Mario
Classic platformer with jumping, movement, enemies, and coins.
⑧ Super Mario 3D Racer
3D racing game showcasing V4's 3D rendering capabilities.
⑨ Early Gray-Release Minecraft
Earlier gray-release version already produced impressive results. Official version improves further.
⑩ One-Sentence Game Generation
Complete game from a single sentence with stunning results.
💰 Super-Opus Capability at 1/90th the Price
| Billing | V4 Pro (Off-Peak) | V4 Pro (Peak) | V4 Flash (Off-Peak) | V4 Flash (Peak) | Claude Opus 4.8 |
|---|---|---|---|---|---|
| Cache Hit | ¥0.025 | ¥0.05 | ¥0.02 | ¥0.04 | $3.75 |
| Cache Miss | ¥3 | ¥6 | ¥1 | ¥2 | $15 |
| Output | ¥6 | ¥12 | ¥2 | ¥4 | $75 |
Per million tokens. DeepSeek in RMB, Claude in USD.
🤔 What This Means
- New era of AI coding: from "code assistant" to "one-sentence product builder"
- Chinese AI surpasses Opus for the first time: DeepSeek becomes the 3rd provider with super-Opus capability
- Price disruptor: super-Opus at 1/90th the price — developer's dream
- Official launch imminent: expected mid-July 2026
Tests based on gray-release version; official release may include further optimizations. Capability assessments are based on independent tester comparisons, not official benchmark data. DeepSeek V4 official expected to fully launch mid-July 2026.