Solar Open 2

Solar Open 2 places in the top three on 3 benchmarks.

Upstage Released 22 Jul 2026 Family Solar Open The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Upstage Jul 2026

Open weights Mid-size

No Epoch Capabilities Index score yet

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.

Benchmark	Score	Rank	Source
IFBench	80%	#8 of 70	Model card
MMLU-Pro	86.2%	#18 of 151	Model card
CLIcK	90.7%	#1 of 4	Model card
KMMLU-Pro	78.4%	#2 of 7	Model card
MultiChallenge	61%	#18 of 36	Model card
Humanity's Last Exam	28.8%	#78 of 147	Model card
AA-LCR (Artificial Analysis Long Context Reasoning)	62.3%	#18 of 31	Model card
HAE-RAE Bench	73.8%	#2 of 3	Model card

Benchmark	Score	Rank	Source
GPQA Diamond	86.3%	#63 of 284	Model card
HMMT 2026	93.9%	#4 of 18	Model card
AIME 2026	95.7%	#8 of 34	Model card
HRM8K	92.2%	#1 of 3	Model card
Ko-AIME 2025 (Upstage)	97.7%	#1 of 2	Model card

Benchmark	Score	Rank	Source
LiveCodeBench v6	92.4%	#3 of 76	Model card
SWE-bench Verified	70.4%	#74 of 150	Model card
ArtifactsBench	55.9%	#3 of 5	Model card

Benchmark	Score	Rank	Source
Terminal-Bench Hard	28.3%	#5 of 11	Model card
τ³-bench Banking	19.6%	#13 of 20	Model card
MCP Atlas	58.2%	#35 of 40	Model card

Benchmark	Score	Rank	Source
KBank-MMLU (Upstage)	80.8%	#1 of 3	Model card
KorMedMCQA	93%	#2 of 4	Model card
KBL	75.5%	#3 of 4	Model card
GDPval-AA v2	1,128	#24 of 26	Model card
APEX-Agents	16.6%	#12 of 12	Model card
Ko-GDPval	86.8%	#2 of 2	Model card

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

Every result in the longer documents the lab published with it.