DeepSeek
DeepSeek V4 Pro None
Released 2026-04-24 · Data snapshot 2026-10-26
Overall score
39.8
Awaiting benchmarks (insufficient coverage)Benchmark coverage
11.5%
3 third-party benchmarks
Context window
—
tokens
Input price
—
per million tokens
Output price
—
per million tokens
Dimension performance
Reasoning
39.8
Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation
Benchmark details
Reasoning2 items
Mystery Game Puzzles17
Chess Puzzles4
Knowledge1 items
GPQA Diamond73.2
Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.