Laguna S 2.1

Laguna S 2.1.

Poolside Released July 21st, 2026 Family Laguna The lab's model card Compare with others

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Poolside Jul 2026

Laguna S 2.1

Open weights Mid-size

149.0 #101 of 404

Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.

GlobeBench 2.45% #19 /19
SWE-bench Multilingual 78.5% #17 /73
OpenAI MRCR v2 4.49% #46 /47

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

Benchmark	Score	Rank	Source
BullshitBench	23.6%	#64 of 107	Official leaderboard
BullshitBench V2	22%	#89 of 129	Official leaderboard
StudyArena Text	1,193	#66 of 85	Official leaderboard
OpenAI MRCR v2	4.49%	#46 of 47	Official leaderboard

Coding

Benchmark	Score	Rank	Source
SWE-bench Multilingual	78.5%	#17 of 73	Lab model card
SWE-Bench Pro	59.4%	#29 of 81	Lab model card
SWE Atlas	46.2%	#11 of 14	Lab model card
DeepSWE	40.4%	#53 of 56	Lab model card

Agents and tools

Benchmark	Score	Rank	Source
Terminal-Bench 2.1	70.2%	#39 of 56	Lab model card
RuneBench	2.82	#67 of 76	Official leaderboard
Toolathlon-Verified	49.7%	#20 of 21	Lab model card

Vision, audio and robotics

Benchmark	Score		Rank	Source
GlobeBench	2.45%		#19 of 19	Official leaderboard

Safety and security

Benchmark	Score		Rank	Source
nocot-bench (NCRI)	62.5		#132 of 185	Official leaderboard

Its lab's numbers put it at 149.0, number 101 of 404

The Self-Reported Index fits one score to the 6 capability results Poolside reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 145.3 to 152.6. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Introducing Laguna S 2.1 (Poolside blog) Jul 21, 2026