DeepSeek V4 Pro Max
| Released | 2026-04-24 |
|---|---|
| Price per 1M | $1.65 in · $3.30 out |
| Overall score | 56.2 · rank 181 |
| Context window | 1,000,000 tokens |
| Provider | DeepSeek |
| Weights | Open weights |
| Configuration | Max |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.2 | 181 | 19 |
| Overall: Coding | 56.1 | 177 | 11 |
| Overall: Reasoning | 55.6 | 182 | 11 |
| Overall: Agentic work | 57.8 | 163 | 10 |
| Overall: Frontend | 53.5 | 172 | 5 |
| Coding | 56.1 | 164 | 4 |
| Agents | 58.6 | 101 | 3 |
| Reasoning | 57.3 | 170 | 3 |
| Math | 54.0 | 128 | 5 |
| Knowledge | 54.4 | 84 | 3 |
| Frontend | 52.2 | 105 | 1 |
| Value vs price | +4.0 | 150 |
Evidence
Coding 56.1 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 50.0% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 87.5% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 77.6% | Epoch AI | 2026-06-18 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 77.4% | Vals AI | 2026-09-01 |
Agents 58.6 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 11.1% | Vals AI | 2026-11-09 |
| Tax Agent Bench | 25.2% | Vals AI | 2026-11-09 |
| SkillsBench | 51.3% | Vals AI | 2026-10-29 |
Reasoning 57.3 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 12.9% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 19.0% | Epoch AI | 2026-10-13 |
| GPQA Diamond | 89.7% | Epoch AI | 2026-06-16 |
| GPQA Diamond (Vals run) | 89.4% | Vals AI | 2026-09-01 |
Math 54.0 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 45.3% | Epoch AI | 2026-06-17 |
| FrontierMath Tier 4 | 2.4% | Epoch AI | 2026-06-17 |
| OTIS Mock AIME 2024-2025 | 96.7% | Epoch AI | 2026-06-17 |
| ProofBench v1.1 | 16.0% | Vals AI | 2026-11-09 |
| MathArena Final-Answer Competitions | 76.6% | MathArena | 2026-11-11 |
| ProofBench | 16.0% | Epoch AI | 2026-11-11 |
Knowledge 54.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 87.2% | Vals AI | 2026-09-01 |
| SimpleQA Verified | 47.0% | Epoch AI | 2026-08-27 |
| Legal Research Bench | 23.1% | Vals AI | 2026-11-09 |
Frontend 52.2 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 49.9% | Vals AI | 2026-11-09 |
Names matched to this model
deepseek-v4-pro-max