Ctrl K
Back to models

Upstage

Solar Open2 250B

  • Released
  • Open weights
  • Upstage Solar License
Compare
Intelligence Index

Reasoning setting

24.7
Estimated · Artificial Analysis v4.3.2
Context window
1.05M tok

Performance profile

ReasoningRank #34 of 107
85.7%
GPQA Diamond
CodingRank #39 of 94
48.0%
SciCode

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
24.7

Pricing & access

No API offering listed in our tracked sources.

Run locally

Original download
500.6 GB
App memory
Unverified
Documented software
vLLM · Upstage forkSetup guide (opens in a new tab)
Find GGUF downloads (opens in a new tab)Original weights (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Solar Open2 250B · Reasoning#53 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 50A.X-K2Reasoning29.6%
  6. 51Solar Pro 4Reasoning29.2%
  7. 52Qwen3.5 397B A17BReasoning29.0%
  8. 53Solar Open2 250BReasoning28.5%
  9. 54Nemotron 3 Ultra 550B A55BReasoning28.4%
  10. 55Qwen3.5 122B A10BReasoning25.2%
  11. 56Nemotron 3.5 Bolt 74B-A9BReasoning24.7%

Peers use their best measured result on this benchmark.