# DeepSeek V4 ProNon-thinking > Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-pro-off. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-pro-off. DeepSeek Canonical URL: https://benchize.com/models/deepseek-v4-pro-off Last updated: Thu, 22 Oct 2026 07:10:12 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. DeepSeek ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Terminal-Bench 2.1 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Amedium.md) | 59.39% | SE ±1.6 pp | 36 / 43 | $0.39 | 1,744.66source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.394 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.387055 \| USD \| per_test \| Lower is better \| \| `latency` \| 1744.656 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.6 pp sourcePopulation 76 stderr 1.603 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/medium/deepseek~1deepseek-v4-pro` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 31.01% | — | 120 / 125 | $1.37 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3101 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.3449 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.3693 \| USD \| per_rollout \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort none sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0067 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label DeepSeek V4 Pro Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/DeepSeek%20V4%20Pro/none/extended` | | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 17.64% | — | 120 / 125 | $1.55 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.1764 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.2 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.5548 \| USD \| per_rollout \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort none sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.01 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label DeepSeek V4 Pro Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/DeepSeek%20V4%20Pro/none/main` | | | | | | | | | [Terminal-Bench 2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aoverall.md) | 50.19% | SE ±1.5 pp | 35 / 43 | $0.24 | 1,078.16source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.187 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.239191 \| USD \| per_test \| Lower is better \| \| `latency` \| 1078.158 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.5 pp sourcePopulation 76 stderr 1.498 tokenTotals {"cache_read_tokens":34026923,"cache_write_tokens":0,"input_tokens":36128386,"output_tokens":3648724,"reasoning_tokens":2947326} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro` | | | | | | | | | [Terminal-Bench 2.0 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Amedium.md) | 67.27% | SE ±6.39 pp | 8 / 23 | — | 1,340.41source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.273 \| percent \| reported \| Higher is better \| \| `latency` \| 1340.408 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.39 pp sourcePopulation 67 stderr 6.385 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/medium/deepseek~1deepseek-v4-pro` | | | | | | | | | [Terminal-Bench 2.0 / hard](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Ahard.md) | 33.33% | SE ±8.75 pp | 9 / 23 | — | 2,457.42source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| \| `latency` \| 2457.415 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.75 pp sourcePopulation 67 stderr 8.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/hard/deepseek~1deepseek-v4-pro` | | | | | | | | | [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 14% | — | 148 / 191 | — | — | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.14 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.66 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 0.4867 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort none suite v2 thinkingEnabled false ### Reported statistics acceptedCount 66 answeredCount 100 clearCount 14 errorCount 0 partialCount 20 rank 188 refusalCount 0 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) Source bullshitbench Original model label deepseek/deepseek-v4-pro Source version v2 Observed 2026-10-22T03:10:12.603Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/187` | | | | | | | | | [Terminal-Bench 2.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Aoverall.md) | 56.18% | SE ±5.29 pp | 8 / 23 | $0.18 | 828.34source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.18 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.179637 \| USD \| per_test \| Lower is better \| \| `latency` \| 828.342 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.29 pp sourcePopulation 67 stderr 5.289 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro` | | | | | | | | | [Terminal-Bench 2.0 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2%3Aeasy.md) | 75% | SE ±25 pp | 9 / 23 | — | 18,430.61source duration | [Vals AI · 2.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75 \| percent \| reported \| Higher is better \| \| `latency` \| 18430.614 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±25 pp sourcePopulation 67 stderr 25 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2.T48tPR4O.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.0 Observed 2026-10-22T02:10:29.313Z Evidence SHA-256 `38e640d995259778e531f048b2f2c7b3b281cb05b56be643ddc9dc53eb85adf7` Source locator `/tasks/easy/deepseek~1deepseek-v4-pro` | | | | | | | | | [Terminal-Bench 2.1 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aeasy.md) | 66.67% | SE ±8.33 pp | 37 / 43 | $5.32 | 23,989.01source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.322002 \| USD \| per_test \| Lower is better \| \| `latency` \| 23989.013 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.33 pp sourcePopulation 76 stderr 8.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/easy/deepseek~1deepseek-v4-pro` | | | | | | | | | [Terminal-Bench 2.1 / hard](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Ahard.md) | 31.11% | SE ±2.22 pp | 32 / 43 | $0.71 | 3,198.54source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.111 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.7096 \| USD \| per_test \| Lower is better \| \| `latency` \| 3198.535 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning false Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.22 pp sourcePopulation 76 stderr 2.222 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/hard/deepseek~1deepseek-v4-pro` | | | | | | | | --- Cite as: DeepSeek V4 ProNon-thinking — Benchize, https://benchize.com/models/deepseek-v4-pro-off (retrieved 2026-10-22)