DeepSeek v4 Pro (high)
ModelOpen sourceActiveby DeepSeek · family “deepseek-v4-pro”
Epoch Capabilities Index
Not scored by Epoch AI
Released
24 Apr 2026
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (13)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 41.2% | 63% | max | — | External ↗ |
| DTBench | reasoning | 90.7% | 92% | max | — | External ↗ |
| Surface Evolver Bench | science | 40.0% | 42% | high | — | External ↗ |
| FrontierMath-Tiers-1-3-v2-Private | math | 45.3% ±3.0 | 48% | max | 17 Jun 2026 | Eval log ↗ |
| FrontierMath-Tier-4-v2-Private | math | 2.4% ±2.4 | 2% | max | 17 Jun 2026 | Eval log ↗ |
| CL-bench Life | long-context | 13.5% | 61% | high | — | External ↗ |
| ProofBench | math | 16.0% | 16% | max | — | External ↗ |
| Chess Puzzles | games | 20.0% ±4.0 | 28% | max | 16 Jun 2026 | Epoch ↗ |
| SimpleQA Verified | knowledge | 47.0% ±1.6 | 62% | max | 27 Aug 2026 | Eval log ↗ |
| WeirdML | coding | 48.9% ±0.0 | 52% | max | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 96.7% ±2.0 | 97% | max | 17 Jun 2026 | Epoch ↗ |
| SWE-Bench verified | coding | 77.6% ±1.9 | 93% | max | 18 Jun 2026 | Eval log ↗ |
| GPQA diamond | science | 90.9% ±2.0 | 95% | high | 6 Aug 2026 | Eval log ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
No data recorded for this period
0 observations (OpenRouter listing). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
- Benchmark33d agoEpoch AI evaluates DeepSeek v4 Pro (high)Epoch AI Benchmarking Hub
- Open release5mo agoDeepSeek releases DeepSeek v4 Pro (high)Epoch AI Benchmarking Hub