BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Humanity's Last Exam

Benchmark Family
Humanity's Last Exam
Organization
Center for AI Safety
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedhumanitys-last-exam/defaultACTIVE5
No toolshumanitys-last-exam/no-toolsACTIVE397
With toolshumanitys-last-exam/with-toolsACTIVE9

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-043HYPERCLOVAXSEEDTHINK32B-003 HyperCLOVA X SEED Think (32B) Humanity's Last Exam No tools Overall 5.5% Unknown Primary source NAVER-HYPERCLOVAXSEEDTHINK32B
BR-044HYPERNOVA60B2605-003 HyperNova 60B 2605 Humanity's Last Exam No tools Overall 15.1% Unknown Primary source MVSC-HYPERNOVA60B2605
BR-045INTELLECT3-003 INTELLECT-3 Humanity's Last Exam No tools Overall 12.1% Unknown Primary source PRIME-INTELLECT3
BR-046NEXN2PRO-003 Nex-N2-Pro Humanity's Last Exam No tools Overall 32.4% Unknown Primary source NEXAI-NEXN2PRO
BR-047LONGCATFLASHLITE-003 LongCat Flash Lite Humanity's Last Exam No tools Overall 6% Unknown Primary source LCAT-LONGCATFLASHLITE
BR-048MOTIF2127BREASONING-003 Motif-2-12.7B-Reasoning Humanity's Last Exam No tools Overall 8.2% Unknown Primary source MOTIF-MOTIF2127BREASONING
BR-049NANBEIGE413B-003 Nanbeige4.1-3B Humanity's Last Exam No tools Overall 10% Unknown Primary source NANB-NANBEIGE413B
BR-051TRINITYLARGETHINKING-003 Trinity Large Thinking Humanity's Last Exam No tools Overall 14.7% Unknown Primary source ARCEE-TRINITYLARGETHINKING
BR-052FALCONH1R7B-003 Falcon-H1R-7B Humanity's Last Exam No tools Overall 10.8% Unknown Primary source TIIUA-FALCONH1R7B
BR-053COGITOV21-002 Cogito v2.1 Humanity's Last Exam No tools Overall 11% Unknown Primary source DPCOG-COGITOV21
BR-054OPENCHAT351210-003 OpenChat 3.5 (1210) Humanity's Last Exam No tools Overall 4.8% Unknown Primary source OPCHT-OPENCHAT351210