ModelsSelected

Upstage releases Solar Mini 4 model

Why we picked it

Solar Mini 4 establishes a new Pareto optimal point for models under 3B active parameters, offering strong long-context reasoning at 83% on AA-LCR v1.1. Developers should note its agentic coding weakness at 1% on Terminal-Bench 4.0 and consider its 5x higher task cost compared to GPT-6 Luna (max) despite similar per-token pricing.

Upstage has released Solar Mini 4, a proprietary reasoning model with 35B total and 3B active parameters.

Body

It scores 24 on the Artificial Analysis Intelligence Index, 16 points higher than Solar Pro 3, and costs $0.10/$0.

40 per 1M input/output tokens.The model generates 208 tokens/s but averages 7.

1 minutes per task due to high token usage.

Original · Artificial Analysis

Korean AI Lab 🇰🇷 Upstage has released Solar Mini 4 which scores 24 on the Artificial Analysis Intelligence Index, but costs ~5x as much per task as GPT-6 Luna (max) despite similar per-token prices

Upstage has released Solar Mini 4, a new proprietary reasoning model. Upstage reports 35B total and 3B active parameters, setting a new Pareto optimal point on Intelligence Index vs. Active Parameters for models under 3B active parameters. It also scores 16 points higher than Upstage's previous-generation flagship, Solar Pro 3 (8), and cuts per-token pricing by a third to $0.10/$0.40 per 1M input/output tokens.

Key results:

➤ Strong for its reported active parameter size: Solar Mini 4 scores 6 points higher than Qwen3.6 35B A3B (Reasoning), which has the same 3B active parameters, and 1 point higher than Nemotron 3 Ultra, which has 55B active. As a proprietary model, its size cannot be independently verified.

➤ Long context reasoning is a relative strength: It scores 83% on AA-LCR v1.1, matching MiniMax-M3 and GPT-6 Luna (max), and ahead of Gemini 3.8 Flash (high) and GPT-6 Astra (max) at 81%. It also scores 48% on SciCode, ahead of MiniMax-M3 and Inkling (xhigh) at 47%.

➤ Fast output, but slow tasks: Solar Mini 4 generates 208 tokens/s as of launch date, faster than GPT-6 Luna (max) at 152 tokens/s. However, it uses 88k output tokens per Intelligence Index task, so it averages 7.1 minutes per task.

➤ Agentic coding is a relative weakness: It scores 1% on Terminal-Bench 4.0 and 22% on AutomationBench-AA. On agentic knowledge work, it scores 1072 Elo on GDPval-AA and 872 Elo on AA-Briefcase, close to Inkling (xhigh).

➤ Low knowledge accuracy, but also relatively high non-hallucination rate: Solar Mini 4 scores -11 on AA-Omniscience with 18% accuracy. It abstains on about half of the questions, and scores 64% on non-hallucination rate, higher than Inkling (xhigh) at 32% and GPT-6 Luna (max) at 23%.

Additional model details:

➤ Context window: 1M tokens

➤ Max output tokens: 262k

➤ License: Proprietary, with weights not released

➤ Parameters: 35B total, 3B active (reported by Upstage)

➤ Modalities: Text input and output only

➤ Knowledge cutoff: February 2026

➤ Pricing: $0.10/$0.40/$0.01 per 1M input/output/cache hit tokens

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Solar Mini 4, Upstage, reasoning models, long context.

Source attribution: curated from Artificial Analysis (@ArtificialAnlys). Cross-source corroboration: 2 independent sources have covered this development (including AI21 Labs), confirming industry-wide signal strength.