# DeepSeek V4.1 Flash 1017High > Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-1-flash-1017-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-1-flash-1017-high. DeepSeek Canonical URL: https://benchize.com/models/deepseek-v4-1-flash-1017-high Last updated: Thu, 22 Oct 2026 09:10:07 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. DeepSeek ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [WeirdML v3](https://benchize.com/benchmarks/weirdml%3Av3.md) | 0.09source score | Range 0.08–0.1 | 13 / 25 | — | [weirdml · b0120fe](https://htihle.github.io/assets/data/weirdml_v3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.09190925681818181 \| source_score \| reported \| Higher is better \| \| `mean_final_best` \| 0.1992338431818182 \| source_score \| reported \| Higher is better \| ### Configuration budget {"kind":"equivalent_tokens","limit":50000000,"start":500000} harness codex_cli Reasoning effort high sourceConfiguration deepseek-v4.1-flash-1017-inferencenet-high-codex ### Reported statistics Uncertainty Reported interval: 0.08–0.1 interval [0.07993782374418672,0.10368927467687615] intervalMethod {"assumptions":"Independent fresh runs; approximately normal scores; shared variance prior. Pool fitted within analysis mode, including incomplete models; pool estimation uncertainty is not propagated.","confidence":0.95,"draws":10000,"fixed_tasks":true,"method":"partially_pooled_variance","pool":{"degrees_of_freedom":1533,"fallback":false,"prior_df":4,"variance":0.0026383113392869583},"seed":20260915,"unit":"run"} runCount 71 taskCount 11 ### Source [Original source](https://htihle.github.io/assets/data/weirdml_v3.json) Source weirdml Original model label DeepSeek V4.1 Flash 1017 (high, InferenceNet) Source version b0120fe Observed 2026-10-22T04:50:05.075Z Evidence SHA-256 `82c3a8de423b23ca0af9761429299a2f21edb0b819e947fdc863f8b5ea4a49b8` Source locator `/rows/12` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 68.61% | — | 59 / 243 | 0.15usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6861111111111112 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.14693756500000005 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup deepseek-v4-1-flash-1017 modelType CoT Reasoning effort high sourceModelVersion deepseek-v4-1-flash-1017-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label DeepSeek V4.1 Flash 1017 (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/291` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,041.1 | Range 1,985.5–2,086.2 | 27 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2041.1 \| rating \| reported \| Higher is better \| \| `overall` \| 81.09 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 72.92 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 80.92 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 73.4 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 81.21 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 88.84 \| source_score \| rubric \| Higher is better \| \| `slop` \| 84.15 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 95.38 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.24 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 79.59 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 79.45 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 80.04 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort high scoreScope 10_task_current sourceConfiguration deepseek-v4-1-flash-1017-high-or thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,985.5–2,086.2 interval [1985.5,2086.2] rank 27 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label DeepSeek V4.1 Flash 1017 (high) Evaluated 2026-10-17 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/26` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 94.12% | — | 13 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.12 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 82.08 \| percent \| category \| Higher is better \| \| `language` \| 100 \| percent \| category \| Higher is better \| \| `utility` \| 97.04 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.95 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.33 \| percent \| category \| Higher is better \| \| `rule_following` \| 84.05 \| percent \| category \| Higher is better \| \| `hallucination` \| 99.51 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4.1 Flash 1017 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4.1 Flash 1017 (Reasoning, High) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/18` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 94.5% | — | 38 / 245 | 0.06usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.945 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.055511946 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup deepseek-v4-1-flash-1017 modelType CoT Reasoning effort high sourceModelVersion deepseek-v4-1-flash-1017-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label DeepSeek V4.1 Flash 1017 (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/290` | | | | | | | --- Cite as: DeepSeek V4.1 Flash 1017High — Benchize, https://benchize.com/models/deepseek-v4-1-flash-1017-high (retrieved 2026-10-22)