DeepSeek V4 Pro vs GPT-6 Luna
| Spec | DeepSeek V4 Pro | GPT-6 Luna |
|---|---|---|
| Respan Index | 49.2 (#44) | 48.6 (#45) |
| Blended price per 1M | $0.585 | $0.2 |
| Context window | 1M | 1.1M |
| Input / output per 1M | $0.28 / $1.5 | $0.1 / $0.5 |
| Max output | 384K | 128K |
| Input | text | text, vision |
| Released | 2026-08-13 | 2026-09-22 |
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 | GPT-6 Luna |
|---|---|---|
| Coding | 29.8 DeepSeek V4 Pro | 28.4 GPT-6 Luna |
| Agents | 59.7 DeepSeek V4 Pro | 60.0 GPT-6 Luna |
| Reasoning | 52.8 DeepSeek V4 Pro | 57.1 GPT-6 Luna |
| Knowledge & language | 52.6 DeepSeek V4 Pro | 38.9 GPT-6 Luna |
| Human preference | 56.0 DeepSeek V4 Pro | 55.6 GPT-6 Luna |
Benchmarks both report
DeepSeek V4 Pro leads on 15 of the 21 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek V4 Pro | GPT-6 Luna |
|---|---|---|
| LMArena Elo | 1464 | 1441 |
| LMArena WebDev (LMArena) | 1581 | 1578 |
| LMArena Agent (LMArena) | -0.003 | 0.0064 |
| MirrorCode (Epoch AI) | 33.3% | 26.7% |
| Chess Puzzles (Epoch AI) | 46% | 36% |
| APEX-Agents (Mercor) | 47.3% | 44.3% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 56.1% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 64.6% | 78.9% |
| GPQA Diamond | 91.7% | 90.5% |
| LiveBench Agentic Coding (LiveBench) | 54.9% | 51.2% |
| LiveBench Coding (LiveBench) | 77.2% | 79% |
| LiveBench Data Analysis (LiveBench) | 79.2% | 73.4% |
| LiveBench Instruction Following (LiveBench) | 67.7% | 55.9% |
| LiveBench Language (LiveBench) | 82.1% | 73.8% |
| LiveBench Mathematics (LiveBench) | 95.1% | 89.1% |
| LiveBench Reasoning (LiveBench) | 85.8% | 81.8% |
| Mystery Game Puzzles (Epoch AI) | 43% | 7% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.6% | 98.9% |
| SimpleQA Verified | 52.9% | 41.4% |
| Terminal-Bench 4.0 (Vals AI) | 14.1% | 13.6% |
| DeepSWE v1.1 | 62.7% | 66.6% |
FAQ
Is DeepSeek V4 Pro better than GPT-6 Luna?
DeepSeek V4 Pro scores 49.2 on the Respan Index (#44), ahead of GPT-6 Luna at 48.6 (#45). DeepSeek V4 Pro leads on 15 of the 21 benchmarks both report.
Which is cheaper, DeepSeek V4 Pro or GPT-6 Luna?
DeepSeek V4 Pro lists at $0.28 input and $1.5 output per 1M tokens; GPT-6 Luna at $0.1 and $0.5. GPT-6 Luna is 2.9x cheaper per token at list price.
Which has the larger context window?
DeepSeek V4 Pro accepts 1M tokens and GPT-6 Luna 1.1M tokens.