Who leads the HotpotQA benchmark?

gpt-4o currently leads HotpotQA with a score of 71.3 on f1.

What is the state-of-the-art score on HotpotQA?

The state-of-the-art result on HotpotQA is 71.3 (f1), achieved by gpt-4o as of 2025.

How many models are tracked on HotpotQA?

Codesota tracks 3 models on HotpotQA.

When was the HotpotQA leaderboard last updated?

The HotpotQA leaderboard on Codesota includes results through 2025.

Codesota · Benchmark · HotpotQAHome/Leaderboards/HotpotQA

Unknown

HotpotQA.

Name: HotpotQA Benchmark Results
Creator: Unknown
Published: 2025-01-01
License: https://creativecommons.org/licenses/by/4.0/

113K question-answer pairs requiring reasoning over multiple Wikipedia documents.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

f1

F1 is the reported evaluation metric for HotpotQA. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for f1verifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Edit
01	gpt-4o Multi-hop question answering requiring reasoning over Wikipedia.	paper	71.3	2025	Source ↗	Edit result
02	claude-35-sonnet	paper	68.5	2025	Source ↗	Edit result
03	Claude 3.5 Sonnet	paper	68.5	2025	Source ↗	Edit result

§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards