DeepSeek V4.1 Flash
| Released | 2026-09-10 |
|---|---|
| Price per 1M | $0.039 in · $1.20 out |
| Overall score | 59.0 · rank 38 |
| Context window | 1,000,000 tokens |
| Provider | DeepSeek |
| Weights | Open weights (MIT) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 59.0 | 38 | 43 |
| Overall: Coding | 59.9 | 28 | 31 |
| Overall: Reasoning | 59.3 | 41 | 17 |
| Overall: Agentic work | 59.2 | 41 | 29 |
| Overall: Frontend | 60.1 | 19 | 11 |
| Coding | 60.0 | 28 | 8 |
| Agents | 58.3 | 49 | 10 |
| Reasoning | 61.4 | 34 | 11 |
| Math | 58.8 | 37 | 4 |
| Knowledge | 55.3 | 57 | 2 |
| Frontend | 60.6 | 16 | 2 |
| General | 57.8 | 41 | 5 |
| Multimodal | 57.3 | 33 | 1 |
| Value vs price | +14.5 | 9 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 57.1 ±3.5 | 5 |
| High | 60.2 ±1.4 | 16 |
| Low | 60.0 ±6.7 | 3 |
| Max | 59.0 ±0.9 | 26 |
| Non-reasoning | 42.6 ±4.9 | 5 |
Evidence
Coding 60.0 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierCode | 43.9% | Epoch AI | 2026-11-11 |
| Code Migration v1.1 | 58.9% | Vals AI | 2026-11-09 |
| WeirdML v3 | 6.0% | Epoch AI | 2026-11-11 |
| MirrorCode | 64.4% | Epoch AI | 2026-10-21 |
| IOI | 40.3% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 46.5% | Vals AI | 2026-11-09 |
| SciCode | 51.9% | Epoch AI | 2026-11-11 |
| ProgramBench | 0.5% | Vals AI | 2026-11-09 |
Agents 58.3 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 19.7% | Vals AI | 2026-11-09 |
| SRE Bench | 0.8% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 0.0% | Vals AI | 2026-11-09 |
| APEX-Agents | 39.5% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 74.5% | Vals AI | 2026-10-01 |
| EMB v1.1 (Excel financial modeling) | 67.8% | Vals AI | 2026-11-09 |
| Tax Agent Bench | 26.6% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 65.4% | Vals AI | 2026-11-09 |
| SkillsBench | 69.8% | Vals AI | 2026-10-29 |
| CyberBench v1.1 | 73.7% | Vals AI | 2026-11-05 |
Reasoning 61.4 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 72.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 72.9% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 89.6% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 21.2% | Vals AI | 2026-11-09 |
| GPQA Diamond | 89.8% | Epoch AI | 2026-10-09 |
| CritPt | 14.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 94.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 94.5% | Epoch AI | 2026-11-11 |
| SimpleBench | 66.7% | SimpleBench | 2026-09-12 |
| BioMysteryBench | 67.8% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 3.3% | ARC Prize | 2026-11-11 |
| Chess Puzzles | 48.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 43.0% | Epoch AI | 2026-10-08 |
Math 58.8 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 67.4% | Epoch AI | 2026-10-08 |
| FrontierMath Tier 4 | 26.8% | Epoch AI | 2026-10-08 |
| OTIS Mock AIME 2024-2025 | 98.3% | Epoch AI | 2026-10-08 |
| ProofBench v1.1 | 54.0% | Vals AI | 2026-11-09 |
| ProofBench | 54.0% | Epoch AI | 2026-11-11 |
Knowledge 55.3 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 42.9% | Epoch AI | 2026-10-13 |
| Legal Research Bench | 41.3% | Vals AI | 2026-11-09 |
Frontend 60.6 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 84.7% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,664 | LMArena | 2026-11-09 |
General 57.8 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,577 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 1,540 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,475 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 42.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 74.0% | EQ-Bench | 2026-11-11 |
Multimodal 57.3 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,263 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 88.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 7.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 90.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 88.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 7.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 90.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 67.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 1.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 60.6% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 67.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 1.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 60.6% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.9% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 2.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 3.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-3 | 0.4% | ARC Prize | A stronger configuration result was used |
| CritPt | 0.3% | Epoch AI | A stronger configuration result was used |
| SciCode | 35.5% | Epoch AI | A stronger configuration result was used |
Names matched to this model
deepseek-v4-1-flash