DeepSeek V4 Flash Vision (Reasoning, Max Effort): benchmark results
Provider: DeepSeek. Released 2026-08-21. Access: Open.
Unified ELO 1685 ± 1, rank #143 of 1761 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Long Context Reasoning | 81.33 | Accuracy (%) | 93.3 |
| BenchmarkList ECI | 146.04 | Capability Index (ECI) | 93.3 |
| AA GPQA Diamond | 91.31 | Accuracy (%) | 92.3 |
| Artificial Analysis Intelligence Index | 41.54 | Intelligence Index | 91.1 |
| AA-LCR | 78 | Accuracy (self-reported) | 90.8 |
| AA GDPval | 1581.74 | ELO | 90.7 |
| Tau3 Banking | 41.03 | Success Rate (%) | 86.9 |
| AA CritPt | 10.86 | Accuracy (%) | 86.3 |
| AA Humanity's Last Exam | 34.48 | Accuracy (%) | 86.2 |
| AA Omniscience - Health | 38.9 | Accuracy (%) | 86 |
| AA Omniscience - Science, Engineering & Mathematics | 43.6 | Accuracy (%) | 84.1 |
| AA Omniscience - Humanities & Social Sciences | 38.5 | Accuracy (%) | 83.4 |
Interactive version: theaggregate.ai/model?slug=deepseek-v4-flash-vision-reasoning-max-effort · How It Works · Data refreshed daily, snapshot 2026-09-05.