Skip to main content
1000Reasons

NaijaBench

How well does each AI actually know Nigeria?

A contamination-free benchmark generated from live Nigerian public data — budgets, the knowledge graph, and this week's news. Every question has a verifiable answer, scored automatically (no LLM judge). Frontier models know Nigeria broadly — but they can't answer fresh, specific civic facts (a state's exact budget, today's news). Only a system with the data can.

#ModelOverallBudgetFAACPartyBirthplaceCity→StateZoneNews (fresh)
1Our agent (data-backed)1000 Reasonsdata-backed61%67%100%33%67%100%40%33%
2Gemini 2.5 FlashGoogle43%0%0%0%67%100%100%0%
3Llama 3.1 8BMeta39%0%0%0%33%100%100%0%
4Mixtral 8x7BMistral39%0%0%0%100%100%60%0%
5Nemotron Super 49BNVIDIA35%0%0%0%0%100%80%33%

Fresh / specific facts (exact budgets, FAAC, this week's news) — no model can memorise these; a data-backed system must retrieve them.