DeepSeek V4 Flash (Max): benchmark results
DeepSeek V4 Flash evaluated at the max reasoning-effort setting. Provider: DeepSeek. Released 2026-04-23. Access: Open.
Unified ELO 1643 ± 1, rank #268 of 1761 rated models, from 43 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (CodeForces) | 100 | Score | 96.9 |
| MathArena - APEX Shortlist 2025 | 89.36 | Accuracy (%) | 89.2 |
| LLM Stats (MathArena Apex) | 85.7 | Score (%) | 87.5 |
| LLM Stats Score | 39.48 | LLM Stats Score (conservative rating) | 85.2 |
| ZeroEval GPQA Diamond | 88.1 | GPQA Diamond Score | 84.2 |
| MathArena - ARXIV_FALSE March | 19.64 | Accuracy (%) | 78.6 |
| SuperCLUE-Writing - Mainstream Genre Writing | 82.57 | Score | 76.9 |
| LLM2014 Logic 2026-05 | 50.97 | Median Score | 76.3 |
| Chess Bench LLM | 919 | Lichess Rating | 75.5 |
| LLM Stats (IMO-AnswerBench) | 88.4 | Score (%) | 73.7 |
| Epoch AI - Dtbench | 86.4 | Score | 73.1 |
| MathArena - APEX 2025 | 27.08 | Accuracy (%) | 72.7 |
Interactive version: theaggregate.ai/model?slug=deepseek-v4-flash-max · How It Works · Data refreshed daily, snapshot 2026-09-05.