Solar Open 100B (Reasoning)

Solar Open 100B (Reasoning)

Upstage · Released Dec 17, 2025
Intelligence #592 / 699
18.9 our score
AA Index #208 / 425
15.2 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Solar Open 100B Reasoning is Upstage's open reasoning model, with a general capability result below the level expected for difficult client work. Its instruction-following and long-context measurements are more useful than its terminal result, and no coding index is supplied. The available evidence therefore supports controlled assistance rather than independent execution.

Potential applications include summarisation, content restructuring, research notes, and internal drafting where teams can review outputs. It is not a strong choice for coding agents, complex tool chains, or high-stakes customer-facing content without additional evaluation. Pricing is not supplied, so the business case cannot be established through token economics, and no context-window size is provided.

Consider it for supervised or self-hosted experiments where openness matters. For production marketing and engineering workflows, validate it against a stronger commercial or open alternative first.

Assessed August 9, 2026

Editorial notes

Solar Open 100B Reasoning offers useful instruction following and long-context results in an open model, but limited general reasoning and weak terminal performance restrict it to supervised workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Solar Open 100B Reasoning offers useful instruction following and long-context results in an open model, but limited general reasoning and weak terminal performance restrict it to supervised workflows.

#592 of 699 overall Down 65 this week

Benchmark scores

GPQA Diamond 65.7%
HLE 9.2%
SciCode 26.9%
TerminalBench Hard 2.3%
τ²-Bench 48.2%
IFBench 57.7%
LCR 36%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

15.2 Intelligence Index

How Solar Open 100B (Reasoning) compares

Solar Open 100B (Reasoning) ranks #208 of 425 AI models we track for overall intelligence. Solar Open 100B (Reasoning) is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 15% of models #592
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Solar Open 100B (Reasoning) $0.00 in $0.00 out
Claude Opus 5 $5.00 in $25.00 out
SpaceXAI: Grok 4.6 $2.00 in $6.00 out
Qwen: Qwen3.8 Max $2.00 in $6.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens
Solar Open 100B (Reasoning) 0

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence2.7Technical0Value0Content5.2
Performance profile

Strongest on content. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Solar Open 100B (Reasoning)

How much does Solar Open 100B (Reasoning) cost?

Solar Open 100B (Reasoning) is currently available for free via OpenRouter.

Who created Solar Open 100B (Reasoning)?

Solar Open 100B (Reasoning) is developed by Upstage and was released on December 17, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.