DeepSeek / DeepSeek V4
DeepSeek V4 Pro
Version DeepSeek-V4-Pro-0813 · Released 2026-08-13 · Available
Compare this model ↗01 / EVIDENCE
Benchmark breakdown
| Benchmark | Version | Method | Configuration | Result | Test date | Verified | Source type | Source |
|---|---|---|---|---|---|---|---|---|
| LiveBench code_completion | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 78.261 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench code_generation | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 76.056 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench javascript | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 68.182 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench AMPS_Hard | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 98 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench olympiad | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 91.286 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench theory_of_mind | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 84.615 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
| LiveBench zebra_puzzle | 2026-06-25 | Public table; published model effort variant | deepseek-v4-pro-0813 | 96.75 % | not published | 2026-09-30 | benchmark maintainer | View source ↗ |
02 / COST
Price & speed
Input / 1M tokens $1.32
Output / 1M tokens $3.96
Cached input / 1M —
Batch input / 1M —
Batch output / 1M —
Speed No comparable observation yet
Price verified 2026-09-29
Price scope API ID deepseek-v4-pro. Peak cache-miss input rate; off-peak and cache-hit rates differ
Price source Official pricing ↗
02A / PERFORMANCE
Measured speed
No sourced speed measurement at a stated effort level yet.
03 / PROFILE
Capabilities
04 / CONTEXT
Strengths & limitations
Coverage: 73% · Limited evidence · 7 observations · 1 source domains (1 independent).
Why no Overall AIQuantumScore?
Qualified category evidence: coding, reasoning, math, agents. An overall score is withheld because only 1 independent source domains (minimum 2). Evidence still missing or lacking comparable overlap: research, multimodal, speed.
05 / HISTORY
Version & price history
Version DeepSeek-V4-Pro-0813 · released 2026-08-13.
2026-09-29: $1.32 input / $3.96 output per 1M tokens · Price source ↗
06 / SOURCES
Source records
- DeepSeek V4 Pro official documentation ↗ · verified 2026-09-29
- DeepSeek official pricing ↗ · verified 2026-09-29
DATED EVIDENCE
History
Standard API price history
- 2026-09-29: 1.98 USD / 1M · 75% input / 25% output USD per 1M · source ↗
One observation; no trend can be inferred.
LiveBench code_completion / 2026-06-25 / %
- 2026-09-30: 78.261 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench code_generation / 2026-06-25 / %
- 2026-09-30: 76.056 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench javascript / 2026-06-25 / %
- 2026-09-30: 68.182 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench AMPS_Hard / 2026-06-25 / %
- 2026-09-30: 98 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench olympiad / 2026-06-25 / %
- 2026-09-30: 91.286 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench theory_of_mind / 2026-06-25 / %
- 2026-09-30: 84.615 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
LiveBench zebra_puzzle / 2026-06-25 / %
- 2026-09-30: 96.75 result · Public table; published model effort variant · evaluation date not published; verification date shown · source ↗
One observation; no trend can be inferred.
Category score history
No two comparable ranking snapshots have been recorded yet.
07 / EXPLORE