[KongchangAI]
Benchmark

GDeepVal AAVR

A benchmark metric whose specific evaluation content is not publicly disclosed.

Timeline (last 90 days)

Oct 22

Leaked data shows Gemini 4 Pro scoring 88.7% on DeepSwe V1.1, 95.3% on Terminal Bench 2.1, 86.8% on OS World 2.0, and 20% on GDeepVal AAVR, with context expanded to 2 million tokens and pricing at $2.25 per million tokens for input and $11.25 for output.

Unverified50%

All Facts (1)

Unverified

Leaked data shows Gemini 4 Pro scoring 88.7% on DeepSwe V1.1, 95.3% on Terminal Bench 2.1, 86.8% on OS World 2.0, and 20% on GDeepVal AAVR, with context expanded to 2 million tokens and pricing at $2.25 per million tokens for input and $11.25 for output.

50%

Source Articles

DeepSeek V4.1 Pro Enters Testing, Gemini 4 Pro Benchmark LeakedOct 22