# DeepSeek V4.1 FlashNon-thinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-1-flash-off. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-1-flash-off.

DeepSeek

Canonical URL: https://benchize.com/models/deepseek-v4-1-flash-off
Last updated: Thu, 22 Oct 2026 04:30:12 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 |  |
| --- | --- | --- | --- | --- | --- | --- |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 7.83% | — | 201 / 213 | 0.00587usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.07833333333333332 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.005873885999999999 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup deepseek-v4-1-flash modelType CoT sourceModelVersion deepseek-v4-1-flash-none thinkingEnabled false ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label DeepSeek V4.1 Flash (None) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/265` |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,627.1 | Range 1,585.1–1,670.5 | 65 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1627.1 \| rating \| reported \| Higher is better \| \| `overall` \| 76.81 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 67.47 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.79 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 65.76 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 79.05 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 80.83 \| source_score \| rubric \| Higher is better \| \| `slop` \| 80.79 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.12 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 78.43 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 75.95 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 75.73 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 73.62 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort none scoreScope 10_task_current sourceConfiguration deepseek-v4-1-flash-none-or thinkingEnabled false ### Reported statistics Uncertainty Reported interval: 1,585.1–1,670.5 interval [1585.1,1670.5] rank 66 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label DeepSeek V4.1 Flash (no thinking) Evaluated 2026-10-08 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/65` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 1.25% | — | 183 / 212 | 0.01usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0125 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.010176125000000005 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup deepseek-v4-1-flash modelType CoT sourceModelVersion deepseek-v4-1-flash-none thinkingEnabled false ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label DeepSeek V4.1 Flash (None) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/268` |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 0.34% | — | 36 / 53 | 734.73usd | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.003431694493873915 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 734.7252066 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup deepseek-v4-1-flash modelType CoT sourceModelVersion deepseek-v4-1-flash-none thinkingEnabled false ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label DeepSeek V4.1 Flash (None) Source version v3 Observed 2026-10-21T16:34:21.112Z Evidence SHA-256 `1aaee2199f8c6d9b5a589aab2fd2480a729e9132f8cf8fbf7b49f81dbd5b2c49` Source locator `/evaluations/90` |  |  |  |  |  |  |

---
Cite as: DeepSeek V4.1 FlashNon-thinking — Benchize, https://benchize.com/models/deepseek-v4-1-flash-off (retrieved 2026-10-22)