DeepSeek V4 Pro
Released 24 Apr 2026$1.32 input, $3.96 output per million tokens1M context1.6T total / 49B activemitAlso written as DS-V4-Pro Max, DeepSeek-V4-Pro, deepseek/deepseek-v4-pro-0813, deepseek/deepseek-v4-pro, DeepSeek V4 Pro 0813, deepseek-v4, deepseek-v4-pro, DeepSeek-V4-pro, deepseek-v4-pro-0813, DeepSeek V4, DeepSeek-V4-Pro-MaxCompare with other models
- Clinical Benchmarks Index
- 60.0rank 44 of 148; 60.0 × 1 = 60.0, from 4 of 10 boards
- Boards
- 5 of 13
- Results
- 166 on secondary measures
- Latest measurement
- Sep 2026
Results
Each line is placed on its own board. Dark tick: the board leader.
Documentation and coding
- MedScribe (Vals AI)model ID deepseek/deepseek-v4-pro-0813; max_output_tokens=30000; reasoning_effort=max80.17Rank 55 of 105Leader Claude Opus 5.5 91.43
- MedScribe (Vals AI)model ID deepseek/deepseek-v4-pro; max_output_tokens=128000; reasoning_effort=max75.14Rank 77 of 105Leader Claude Opus 5.5 91.43
- MedCode (Vals AI)model ID deepseek/deepseek-v4-pro-0813; reasoning_effort=max; max_output_tokens=3000042.47Rank 47 of 103Leader Claude Opus 5 63.57
- MedCode (Vals AI)model ID deepseek/deepseek-v4-pro; reasoning_effort=max; max_output_tokens=12800040.45Rank 61 of 103Leader Claude Opus 5 63.57
EHR and workflow agents
- PhysicianBenchPass@1 over 3 runs; Pass^3 6.0; shared FHIR tool harness; up to 100 turns; high reasoning when supported18.7Rank 15 of 21 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
- 14.2Rank 24 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 13.8Rank 25 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 11.1Rank 29 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
- 10.7Rank 31 of 43 here, 45 models on the boardLeader erius + claude-opus-5 54.7
Safety
- MedPICzero-shot; independent questions; exact option-set match71.7Rank 4 of 28Leader Gemini-3.1-Pro 80.7
Secondary measures
Safety
- 32.6Rank 3 of 28Leader Gemini-3.1-Pro 48.3
- 81.3Rank 4 of 28Leader Gemini-3.1-Pro 87.7
- 56.8Rank 4 of 28Leader Gemini-3.1-Pro 69.9
- 67.6Rank 5 of 28Leader MedGemma-27B-Text 76.1
- 50.0Rank 7 of 28Leader Gemini-3.1-Pro 77.9
- 24.5Descriptive measure, not ranked
Sources
Open a line for the quote and page.
55MedScribe (Vals AI) model ID deepseek/deepseek-v4-pro-0813; max_output_tokens=30000; reasoning_effo… 80.17
Printed as 80.17%Official leaderboard, measured Sep 2026Configuration: model ID deepseek/deepseek-v4-pro-0813; max_output_tokens=30000; reasoning_effort=maxVals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 55 of 105 (DeepSeek V4 Pro 0813), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro-0813"].55 | DeepSeek V4 Pro 0813 | 80.17%±2.00 | $1.32/$3.96 | 2m36s
Every result from this document77MedScribe (Vals AI) model ID deepseek/deepseek-v4-pro; max_output_tokens=128000; reasoning_effort=m… 75.14
Printed as 75.14%Official leaderboard, measured Sep 2026Configuration: model ID deepseek/deepseek-v4-pro; max_output_tokens=128000; reasoning_effort=maxVals AI MedScribe leaderboard official leaderboard, Vals AI, 3 Sep 2026. Vals AI MedScribe leaderboard, View: All Models, Task: Overall, row 77 of 105 (DeepSeek V4), Accuracy column; Updated 9/29/2026. Rendered BenchmarkView table; configuration from embedded astro-island BenchmarkView props, benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro"].77 | DeepSeek V4 | 75.14%±2.00 | $1.32/$3.96 | 5m46s
Every result from this document47MedCode (Vals AI) model ID deepseek/deepseek-v4-pro-0813; reasoning_effort=max; max_output_tokens… 42.47
Printed as 42.47%Official leaderboard, measured Sep 2026Configuration: model ID deepseek/deepseek-v4-pro-0813; reasoning_effort=max; max_output_tokens=30000Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 47 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro-0813"].47 | DeepSeek V4 Pro 0813 | 42.47%±2.16 | $1.32/$3.96 | 3m01s
Every result from this document61MedCode (Vals AI) model ID deepseek/deepseek-v4-pro; reasoning_effort=max; max_output_tokens=1280… 40.45
Printed as 40.45%Official leaderboard, measured Sep 2026Configuration: model ID deepseek/deepseek-v4-pro; reasoning_effort=max; max_output_tokens=128000Vals AI MedCode leaderboard official leaderboard, Vals AI, 29 Sep 2026. MedCode leaderboard, Overall task, All Models expanded, rank 61 of 103; Accuracy column; board Updated 9/29/2026. Rendered table row; configuration from embedded BenchmarkView props benchmarkView.default.tasks.overall["deepseek/deepseek-v4-pro"].61 | DeepSeek V4 | 40.45%±2.12 | $1.32/$3.96 | 6m23s
Every result from this document4MedPIC zero-shot; independent questions; exact option-set match 71.7
Printed as 71.7Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column Overall; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document15PhysicianBench Pass@1 over 3 runs; Pass^3 6.0; shared FHIR tool harness; up to 100 turns; high… 18.7
Printed as 18.7 ± 2.9Official leaderboard, measured May 2026Configuration: Pass@1 over 3 runs; Pass^3 6.0; shared FHIR tool harness; up to 100 turns; high reasoning when supportedPhysicianBench: Evaluating LLM Agents in Real-World EHR Environments (arXiv 2605.02240v1 PDF) paper, Stanford University (HealthRex; Liu, Chen et al.), 4 May 2026. arXiv HTML 2605.02240v1, Section 5.2, Table 2; DeepSeek V4-Pro row, Pass@1 column (PDF p. 8).Model | Pass@1 | Pass@3 | Pass^3 | #Turns DeepSeek V4-Pro | 18.7 ± 2.9 | 27.9 | 6.0 | 35.3
Every result from this document24CHI-Bench All Domains pass@1; openai-agents harness 14.2
Printed as 14.2%Official leaderboard, measured May 2026Configuration: All Domains pass@1; openai-agents harnessCHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 24, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-05-01; accessed 2026-09-30. Linked submission provenance: run 2026-05-03T08:35:38Z to 2026-05-04T06:59:15Z; submitted_at 2026-05-04T06:59:15Z.24 | openai-agents | deepseek-v4-pro | Open-source | 14.2% | 10.7% | 28.0% | 4.0% | 2026-05-01
Every result from this document- Also printed in CHI-Bench submission manifest: openai-agents + deepseek/deepseek-v4-pro, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
25CHI-Bench All Domains pass@1; hermes harness 13.8
Printed as 13.8%Official leaderboard, measured May 2026Configuration: All Domains pass@1; hermes harnessCHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 25, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-05-01; accessed 2026-09-30. Linked submission provenance: run 2026-05-03T06:28:45Z to 2026-05-04T05:51:44Z; submitted_at 2026-05-04T05:51:44Z.25 | hermes | deepseek-v4-pro | Open-source | 13.8% | 8.0% | 25.3% | 8.0% | 2026-05-01
Every result from this document- Also printed in CHI-Bench submission manifest: hermes + openrouter/deepseek/deepseek-v4-pro, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
29CHI-Bench All Domains pass@1; openclaw harness 11.1
Printed as 11.1%Official leaderboard, measured May 2026Configuration: All Domains pass@1; openclaw harnessCHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 29, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-05-01; accessed 2026-09-30. Linked submission provenance: run 2026-05-02T09:01:51Z to 2026-05-04T03:00:01Z; submitted_at 2026-05-04T03:00:01Z.29 | openclaw | deepseek-v4-pro | Open-source | 11.1% | 14.7% | 12.0% | 6.7% | 2026-05-01
Every result from this document- Also printed in CHI-Bench submission manifest: openclaw + openrouter/deepseek/deepseek-v4-pro, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
31CHI-Bench All Domains pass@1; deepagents harness 10.7
Printed as 10.7%Official leaderboard, measured May 2026Configuration: All Domains pass@1; deepagents harnessCHI-Bench leaderboard (actAVA) official leaderboard, actAVA, 12 Aug 2026. CHI-Bench v1.0.0, All Domains, rank 31, Agent/Model and Accuracy columns; PA/UM/CM follow; board last updated 2026-08-12; board Date column 2026-05-01; accessed 2026-09-30. Linked submission provenance: run 2026-05-03T07:35:56Z to 2026-05-05T01:34:20Z; submitted_at 2026-05-05T01:34:20Z.31 | deepagents | deepseek-v4-pro | Open-source | 10.7% | 14.7% | 10.7% | 6.7% | 2026-05-01
Every result from this document- Also printed in CHI-Bench submission manifest: deepagents + openrouter/deepseek/deepseek-v4-pro, submission.model; provenance.started_at / finished_at; results.overall.pass_at_1; retrieved 2026-09-30
4MedPIC, Guideline-following accuracy (GF) zero-shot; independent questions; exact option-set match 81.3
Printed as 81.3Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column GF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document4MedPIC, Counterfactual accuracy (CF) zero-shot; independent questions; exact option-set match 56.8
Printed as 56.8Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column CF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document3MedPIC, Linked counterfactual pair accuracy zero-shot; independent questions; exact option-set match 32.6
Printed as 32.6Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column Pair; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document5MedPIC, Risk activation accuracy zero-shot; independent questions; exact option-set match 67.6
Printed as 67.6Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column Activation; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document7MedPIC, Risk deactivation accuracy zero-shot; independent questions; exact option-set match 50.0
Printed as 50.0Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column Deactivation; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document–MedPIC, Published GF-minus-CF accuracy gap zero-shot; independent questions; exact option-set match 24.5
Printed as 24.5Independent run, measured Aug 2026Configuration: zero-shot; independent questions; exact option-set matchEvaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning paper, Zhitian Hou, Yuhang Liu, Pengkai Wang, Zeyu Liu, Guanghao Zhu, Zheng Liu, Shuo Cai, Congkai Xie, Zhijie Sang, Kun Zeng, Hongxia Yang (The Hong Kong Polytechnic University; InfiX.ai; Sun Yat-sen University), 4 Aug 2026. arXiv:2608.03028v1, Section 4, Table 2 (#S4.T2), row DeepSeek-V4-Pro, column Δ_GF−CF; row order: Model | Overall | GF | CF | Δ_GF−CF | Activation | Deactivation | PairDeepSeek-V4-Pro | 71.7 | 81.3 | 56.8 | 24.5 | 67.6 | 50.0 | 32.6
Every result from this document
Other DeepSeek models: DeepSeek R1, DeepSeek-V3.1, DeepSeek-V3.2-Exp, DeepSeek V4.1 Flash, DeepSeek V4 Flash, DeepSeek V4 Flash 0731