DeepSeek V4
Data snapshot 2026-10-27
Overall score
45.5
Awaiting benchmarks (insufficient coverage)Benchmark coverage
30.8%
8 third-party benchmarks
Context window
—
tokens
Input price
—
per million tokens
Output price
—
per million tokens
Dimension performance
Coding
45.7
Office
45.1
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation
Benchmark details
Coding3 items
Vibe Code Bench49.93
Terminal-Bench 4.011.11
ProgramBench0
Office4 items
Tax Eval v272.08
Corporate Finance v261.38
MedCode40.45
Legal Research23.08
Knowledge1 items
MMLU-Pro87.25
Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.
Score trend
2026-10-262026-10-27
View daily data
| 2026-10-27 | 45.5 |
| 2026-10-26 | 45.3 |