Work Automations
Private 657 tasks; 50 turns; objective completion
- 01
- 02
- 03
- 04
- 05
- 09
DeepSeek V4.1 Flash 1017
Across the task benchmarks we track, DeepSeek V4.1 Flash 1017’s strongest relative results are in knowledge work and work automations. On GDPval-AA v2.1, it scores 1,746 Elo, ranking #5 among 38 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Agent Index ↗v1.2 Preview | Overall agent capability | 40.6 / 100#12 of 26 |
| LiveBench: Coding ↗2.0 / 2026-10-25 | Coding with LiveBench | 96%Joint #3 of 25 |
| LiveBench: Design ↗2.0 / 2026-10-25 | Documents and presentations | 83.4%Joint #3 of 25 |
| GDPval-AA ↗2.1 | Knowledge work | 1,745.77 Elo#5 of 38 |
Model details
| Model | DeepSeek V4.1 Flash 1017 |
|---|---|
| Agent Index v1.2 | 40.6 / 100 · Rank 12 · Preview |
| Creator | DeepSeek (opens in a new tab) |
| Availability | Open source / open weights |
| Context size | 1,000,000 tokens (opens in a new tab) |
| Max output | 393,216 tokens (opens in a new tab) |
| Knowledge cutoff | Not reported |
| License | MIT · Model weights ↗ (opens in a new tab) |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
| Provider / configuration | Contexttokens | InputUSD / 1M tokens | OutputUSD / 1M tokens | LatencyTTFT · seconds | Speedtokens / sec |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 0.355 (opens in a new tab) | 166.806 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) (FAST) | 1,048,576 | $0.60 (opens in a new tab) | $2.40 (opens in a new tab) | 0.182 (opens in a new tab) | 1,021.729 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.144 (opens in a new tab) | $0.576 (opens in a new tab) | 1.651 (opens in a new tab) | 294.279 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.098 (opens in a new tab) | $0.294 (opens in a new tab) | 0.701 (opens in a new tab) | 92.086 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 1.277 (opens in a new tab) | 173.207 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 0.503 (opens in a new tab) | 253.956 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 1.338 (opens in a new tab) | 214.831 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,575 | $0.18 (opens in a new tab) | $0.72 (opens in a new tab) | 1.448 (opens in a new tab) | 363.705 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) (FAST) | 1,048,576 | $0.60 (opens in a new tab) | $2.40 (opens in a new tab) | 1.317 (opens in a new tab) | 1,075.275 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.15 (opens in a new tab) | $0.60 (opens in a new tab) | 0.962 (opens in a new tab) | 248.975 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) (FAST) | 1,048,576 | $0.25 (opens in a new tab) | $1.00 (opens in a new tab) | 1.073 (opens in a new tab) | 393.111 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) (ULTRA CHAT) | 1,048,576 | $0.35 (opens in a new tab) | $1.40 (opens in a new tab) | Not reported | Not reported |
| DeepSeek V4.1 Flash 1017 (max) (ULTRA) | 1,048,576 | $0.35 (opens in a new tab) | $1.40 (opens in a new tab) | 0.996 (opens in a new tab) | 430.879 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.15 (opens in a new tab) | $1.20 (opens in a new tab) | 0.94 (opens in a new tab) | 211.519 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.25 (opens in a new tab) | $1.00 (opens in a new tab) | 0.601 (opens in a new tab) | 233.592 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 1.33 (opens in a new tab) | 391.095 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 1.618 (opens in a new tab) | 149.885 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,000,000 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 0.623 (opens in a new tab) | 243.147 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.24 (opens in a new tab) | $0.96 (opens in a new tab) | 0.803 (opens in a new tab) | 225.044 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.15 (opens in a new tab) | $0.60 (opens in a new tab) | 1.162 (opens in a new tab) | 231.297 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 0.988 (opens in a new tab) | 845.4 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.30 (opens in a new tab) | $1.20 (opens in a new tab) | 0.31 (opens in a new tab) | 382.936 (opens in a new tab) |
| DeepSeek V4.1 Flash 1017 (max) | 1,048,576 | $0.15 (opens in a new tab) | $0.60 (opens in a new tab) | 0.618 (opens in a new tab) | 205.721 (opens in a new tab) |
Benchmark performance
DeepSeek V4.1 Flash 1017 in color, alongside leading models. Latest stored reports, best effort per report date.
AutomationBench-AA ↗
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 1,570.42 Elo | selection: best reported configuration per release · DeepSeek V4.1 Flash 1017 (Max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 66.641% | DeepSeek V4.1 Flash 1017 (Max); Private 657 tasks; 50 turns; objective completion | Artificial Analysis (opens in a new tab)independent |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 68.493% | DeepSeek V4.1 Flash 1017 (High); Private 657 tasks; 50 turns; objective completion | Artificial Analysis (opens in a new tab)independent |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 48.779% | DeepSeek V4.1 Flash 1017 (Non-reasoning); Private 657 tasks; 50 turns; objective completion | Artificial Analysis (opens in a new tab)independent |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 17.2% | selection: best reported configuration per release · DeepSeek V4.1 Flash 1017 (Max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,745.77 Elo | DeepSeek V4.1 Flash 1017 (Max); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| HLE-Diamond1,000 questions / no toolsAccuracy · Higher is better | 25.3% | selection: best reported configuration per release · DeepSeek V4.1 Flash 1017 (Max) · No tools | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 42.6% | subset: full · No tools | DeepSeek ↗ (opens in a new tab)provider reported · 2026-10-17 |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 58.8% | Max effort; competitor result in Moonshot AI report. · subset: full · Tools enabled | Moonshot AI ↗ (opens in a new tab)other |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 44% | subset: text · No tools | DeepSeek ↗ (opens in a new tab)provider reported · 2026-10-17 |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 43.3% | question count: 2158 · reported precision decimals: 1 · DeepSeek V4.1 Flash 1017 (max); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/deepseek-v4-1-flash-1017 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| LiveBench: Agentic2.0 / 2026-10-25Accuracy · Higher is better | 35.7% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: agentic | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Browser Use2.0 / 2026-10-25Accuracy · Higher is better | 67.2% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: browser-use | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Coding2.0 / 2026-10-25Accuracy · Higher is better | 96% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Data Analysis2.0 / 2026-10-25Accuracy · Higher is better | 79.5% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: data-analysis | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Design2.0 / 2026-10-25Accuracy · Higher is better | 83.4% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: design | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Reasoning2.0 / 2026-10-25Accuracy · Higher is better | 89.1% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: reasoning | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Research2.0 / 2026-10-25Accuracy · Higher is better | 79.5% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: research | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 33.838% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · DeepSeek V4.1 Flash 1017 (Max) | Artificial Analysis (opens in a new tab)independent |