DeepSeek V4 Flash Latestopen
~deepseek
68.6#46 of 427 overall
- Input / output
- US$ 0,05 / US$ 0,30 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 08/01/2026 release date
- Weights
- Open
- Speed
- 0 tok/s first token in 0.00 s
Family history
The 2 versions of this family, from first to newest, by release date. Click a point to open that version.
See the data as a table
| Model | Released | Score | Rank | AA Intel. | Elo Arena |
|---|---|---|---|---|---|
| DeepSeek V4 Flash Latest | 08/01/2026 | 68.6 | #46 | — | 1432 |
| DeepSeek V4.1 Flash 1017 | 10/17/2026 | 75.3 | #27 | 32.5 | 1465 |
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1432 | 65% | LMArena |
| Arena WebDev (Elo) weight 1 | 1582 | 72% | LMArena |
| Humanity's Last Exam weight 1 | 38.6 | 87% | Artificial Analysis |
| Terminal-Bench weight 1 | 12.1 | 72% | Artificial Analysis |
| GPQA Diamond | 90.8 | 92% | Artificial Analysis |
| Long-context reasoning | 79.7 | 86% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 61.2 | #32 | Terminal-Bench |
| Coding | 61.2 | #26 | Arena WebDev (Elo) |
| Reasoning | 76.4 | #35 | Humanity's Last Exam, GPQA Diamond |
| Research | 67.8 | #42 | Long-context reasoning |
| Design | 61.2 | #27 | Arena WebDev (Elo) |
| Chat | 57.3 | #70 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.