# DeepSeek V4 Pro 0813High > Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-pro-0813-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-pro-0813-high. DeepSeek Canonical URL: https://benchize.com/models/deepseek-v4-pro-0813-high Last updated: Thu, 22 Oct 2026 06:30:09 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 | | | --- | --- | --- | --- | --- | --- | --- | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 90.21% | — | 57 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.21 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.79 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.72 \| percent \| category \| Higher is better \| \| `language` \| 88.93 \| percent \| category \| Higher is better \| \| `utility` \| 97.9 \| percent \| category \| Higher is better \| \| `reasoning` \| 90.05 \| percent \| category \| Higher is better \| \| `text_editing` \| 93.76 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.72 \| percent \| category \| Higher is better \| \| `hallucination` \| 88.77 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort high Model configuration DeepSeek V4 Pro 0813 (Reasoning, High) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Pro 0813 (Reasoning, High) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/70` | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 44.45% | — | 102 / 125 | $1.5 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4445 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4893 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.4996 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort high sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.076 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label DeepSeek V4 Pro 0813 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/DeepSeek%20V4%20Pro%200813/high/extended` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 59.72% | — | 82 / 243 | 0.6usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5972222222222221 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.5969432040000002 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup deepseek-v4-pro-0813 modelType CoT Reasoning effort high sourceModelVersion deepseek-v4-pro-0813-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label DeepSeek V4 Pro 0813 (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/217` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 87.17% | — | 91 / 245 | 0.31usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8716666666666666 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.3070726955999999 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup deepseek-v4-pro-0813 modelType CoT Reasoning effort high sourceModelVersion deepseek-v4-pro-0813-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label DeepSeek V4 Pro 0813 (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/216` | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 28.55% | — | 103 / 125 | $1.81 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2855 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.318 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.812 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort high sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.106 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label DeepSeek V4 Pro 0813 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/DeepSeek%20V4%20Pro%200813/high/main` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,327.3 | Range 1,242.2–1,388.4 | 88 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1327.3 \| rating \| reported \| Higher is better \| \| `overall` \| 72.29 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 61.6 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 72.53 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 70.62 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 77.88 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 72.74 \| source_score \| rubric \| Higher is better \| \| `slop` \| 77.45 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 93.3 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 75.86 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 68.58 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 69.81 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 69.58 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort unknown scoreScope 10_task_current sourceConfiguration deepseek-v4-pro-0813-or thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,242.2–1,388.4 interval [1242.2,1388.4] rank 90 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label DeepSeek V4 Pro 0813 (high) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/89` | | | | | | | --- Cite as: DeepSeek V4 Pro 0813High — Benchize, https://benchize.com/models/deepseek-v4-pro-0813-high (retrieved 2026-10-22)