DeepSeek V4 Pro vs Qwen3.8-Max
| Spec | DeepSeek V4 Pro | Qwen3.8-Max |
|---|---|---|
| Respan Index | 49.2 (#45) | 52.8 (#35) |
| Blended price per 1M | $0.585 | $2.48 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.28 / $1.5 | $1.65 / $4.95 |
| Max output | 384K | 131K |
| Input | text | text, vision |
| Released | 2026-08-13 | 2026-08-02 |
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 Pro | Qwen3.8-Max |
|---|---|---|
| Coding | 29.8 DeepSeek V4 Pro | 39.3 Qwen3.8-Max |
| Agents | 59.7 DeepSeek V4 Pro | 68.6 Qwen3.8-Max |
| Reasoning | 52.8 DeepSeek V4 Pro | 49.4 Qwen3.8-Max |
| Knowledge & language | 52.6 DeepSeek V4 Pro | 48.1 Qwen3.8-Max |
| Human preference | 55.6 DeepSeek V4 Pro | 58.0 Qwen3.8-Max |
Benchmarks both report
Qwen3.8-Max leads on 12 of the 22 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | DeepSeek V4 Pro | Qwen3.8-Max |
|---|---|---|
| LMArena WebDev (LMArena) | 1581 | 1670 |
| LMArena Elo | 1464 | 1484 |
| LMArena Agent (LMArena) | -0.003 | -0.0091 |
| MirrorCode (Epoch AI) | 33.3% | 52.2% |
| Chess Puzzles (Epoch AI) | 46% | 46% |
| APEX-Agents (Mercor) | 47.3% | 63.3% |
| DeepSWE v1.1 (Datacurve) | 62.8% | 57.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 46.3% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 64.6% | 74.7% |
| GPQA Diamond | 91.7% | 92.6% |
| LiveBench Agentic Coding (LiveBench) | 54.9% | 64.6% |
| LiveBench Coding (LiveBench) | 77.2% | 72.9% |
| LiveBench Data Analysis (LiveBench) | 79.2% | 78.4% |
| LiveBench Instruction Following (LiveBench) | 67.7% | 74.1% |
| LiveBench Language (LiveBench) | 82.1% | 79.7% |
| LiveBench Mathematics (LiveBench) | 95.1% | 91.3% |
| LiveBench Reasoning (LiveBench) | 85.8% | 88.2% |
| Mystery Game Puzzles (Epoch AI) | 43% | 38% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.6% | 100% |
| SimpleQA Verified | 52.9% | 47.3% |
| Terminal-Bench 4.0 (Vals AI) | 14.1% | 34.3% |
| Terminal-Bench 2.1 | 87.9% | 86.6% |
FAQ
Is DeepSeek V4 Pro better than Qwen3.8-Max?
Qwen3.8-Max scores 52.8 on the Respan Index (#35), ahead of DeepSeek V4 Pro at 49.2 (#45). Qwen3.8-Max leads on 12 of the 22 benchmarks both report.
Which is cheaper, DeepSeek V4 Pro or Qwen3.8-Max?
DeepSeek V4 Pro lists at $0.28 input and $1.5 output per 1M tokens; Qwen3.8-Max at $1.65 and $4.95. DeepSeek V4 Pro is 4.2x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.