Which Benchmarks will GPT-5 be benchmarked against, when it is announced?
➕
Plus
8
Ṁ746
Jan 1
76%
SimpleQA
61%
GSM8K
71%
HumanEval
81%
MMLU
84%
GPQA
76%
MATH
52%
MGSM
32%
DROP
52%
Big-Bench-Hard
87%
SWE-Bench

Some flexibility on variations of specific benchmarks. eg SWE-Bench-Hard would resolve SWE-Bench YES.

Get
Ṁ1,000
and
S3.00
Sort by:
© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules