DeepSeek V4.1 Flash Non-reasoning
| Released | 2026-09-10 |
|---|---|
| Price per 1M | $0.039 in · $1.20 out |
| Overall score | 42.7 (early, few results) |
| Context window | 1,000,000 tokens |
| Provider | DeepSeek |
| Weights | Open weights (MIT) |
| Configuration | Non-reasoning |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 42.7 | 5 | |
| Overall: Coding | 42.2 | 5 | |
| Overall: Reasoning | 43.9 | 4 | |
| Overall: Agentic work | 42.7 | 5 | |
| Overall: Frontend | 41.9 | 1 | |
| Coding | 41.9 | 1 | |
| Reasoning | 43.9 | 4 | |
| Value vs price | −4.5 |
Evidence
Coding 41.9 ±4.7
Reasoning 43.9 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 0.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 | 1.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 7.8% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 7.8% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 1.3% | ARC Prize | 2026-11-11 |
| ARC-AGI-3 | 0.3% | ARC Prize | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-3 | 0.5% | ARC Prize | Lower duplicate run on the same benchmark |
Names matched to this model
deepseek-v4-1-flash-non-reasoning