ERNIE 5.0 Thinking Preview
Released · 136 days after ERNIE 4.5 300B A47B
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Global rank#226 of 597 LLMs
TierEfficient
Intelligence Index22.3
Math Index85.0
Reasoning & knowledge
MMLU-Pro
83%
GPQA Diamond
78%
Humanity's Last Exam
13%
Long-context reasoning
7%
Coding
LiveCodeBench
81%
SciCode
38%
Agentic & tool use
Terminal-Bench Hard
25%
τ²-Bench Telecom
84%
Math & instruction following
AIME 2025
85%
IFBench
41%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — ERNIE 5.0 Thinking Preview isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →