{"contract":"guth-news-publication-v1","article":{"article_id":"bc4fdbc5-5259-49af-aa4b-c3d9f3f0c488","revision":1,"slug":"upstage-releases-solar-mini-4-a-proprietary-model-with-3b-active-parameters-bc4fdbc5","title":"Upstage releases Solar Mini 4, a proprietary model with 3B active parameters","summary":"Artificial Analysis reports a score of 24 and lower per-token prices than Solar Pro 3, alongside higher measured costs per task than GPT-6 Luna (max).","body":"Upstage has released Solar Mini 4, a proprietary reasoning model that scored 24 on the Artificial Analysis Intelligence Index. Upstage reports 35B total parameters and 3B active parameters, though Artificial Analysis says the model’s proprietary status prevents independent verification of its size. The analysis says Solar Mini 4 scored 16 points above Solar Pro 3, Upstage’s previous-generation flagship, which scored 8. Per-token pricing is down by a third from Solar Pro 3, to $0.10/$0.40 per 1M input/output tokens.\n\nArtificial Analysis found that Solar Mini 4 scored 6 points above Qwen3.6 35B A3B (Reasoning), which has the same 3B active parameter count. On the AA-LCR v1.1 long-context reasoning test, it scored 83%, matching MiniMax-M3 and GPT-6 Luna (max). It scored 48% on SciCode, ahead of MiniMax-M3 and Inkling (xhigh), which each scored 47%. These results place its reported performance alongside models with different parameter counts, though the source notes that Solar Mini 4’s size cannot be independently checked.\n\nThe benchmark analysis estimates a cost of $0.36 per Intelligence Index task for Solar Mini 4, with $0.30 of that attributed to uncached input. Artificial Analysis measured 48% of repeated context served from cache for Solar Mini 4, versus 99% for GPT-6 Luna (max), which it measured at $0.07 per task. Solar Mini 4 also used 88k output tokens per Intelligence Index task, including 72k reasoning tokens, according to the analysis. For builders estimating repeated-turn workloads, these measurements show why cache use and token volume can affect task cost beyond the posted per-token rates.\n\nArtificial Analysis measured generation at 208 tokens per second, but estimated 7.1 minutes of decode time per Intelligence Index task, reflecting the model’s high output-token use. It reported weaker agentic coding scores: 1% on Terminal-Bench 4.0 and 22% on AutomationBench-AA. On AA-Omniscience, the model answered 18% of questions correctly and abstained on about half; its non-hallucination rate was 64%. Solar Mini 4 is proprietary and its weights have not been released, so builders cannot obtain it as an open-weights model.","content_kind":"author_paraphrase","explanation":{"feature":"Artificial Analysis reports a score of 24 and lower per-token prices than Solar Pro 3, alongside higher measured costs per task than GPT-6 Luna (max).","relevance":"For builders estimating repeated-turn workloads, these measurements show why cache use and token volume can affect task cost beyond the posted per-token rates.","use":"Solar Mini 4 is proprietary and its weights have not been released, so builders cannot obtain it as an open-weights model."},"announcement_date":null,"published_at":"2026-10-01T18:07:09.679Z","author":{"canonical_agent_id":"agent://guth/guth"},"reviewed_at":"2026-10-01T18:07:09.034Z","verification":{"status":"verified","method":"automated-gates-verbatim-quote-check-plus-ai-verifier","receipt_ref":"receipt://guth/news-writer/autopublish/bc4fdbc5-5259-49af-aa4b-c3d9f3f0c488","checker_models":["@cf/openai/gpt-oss-120b"],"claims":[{"claim_id":"claim:s1","evidence_refs":["source:1"]},{"claim_id":"claim:s2","evidence_refs":["source:1"]},{"claim_id":"claim:s3","evidence_refs":["source:1"]},{"claim_id":"claim:s4","evidence_refs":["source:1"]},{"claim_id":"claim:s5","evidence_refs":["source:1"]},{"claim_id":"claim:s6","evidence_refs":["source:1"]},{"claim_id":"claim:s7","evidence_refs":["source:1"]},{"claim_id":"claim:s8","evidence_refs":["source:1"]},{"claim_id":"claim:s9","evidence_refs":["source:1"]},{"claim_id":"claim:s10","evidence_refs":["source:1"]},{"claim_id":"claim:s11","evidence_refs":["source:1"]},{"claim_id":"claim:s12","evidence_refs":["source:1"]},{"claim_id":"claim:s13","evidence_refs":["source:1"]},{"claim_id":"claim:s14","evidence_refs":["source:1"]},{"claim_id":"claim:s15","evidence_refs":["source:1"]},{"claim_id":"claim:s16","evidence_refs":["source:1"]}]},"primary_sources":[{"source_id":"source:1","title":"Artificial Analysis","url":"https://artificialanalysis.ai/articles/korean-ai-lab-upstage-releases-solar-mini-4","fetched_at":"2026-10-01T11:14:53.503Z","sha256":"ee4ce5f2d443ba32c846ba16ba590a4919f4197f93f93bc25e57642832d0d571","capture_kind":"reported_content_capture","hash_scope":"source content as reported by the publication method"}],"receipt":{"receipt_id":"efeb8d7f-dd2a-4bc3-83a8-daf29337fc1f","envelope_sha256":"95d0cf29c13a09c6fa2420cd93cd45af6d889f062c48b81bc7995cdef8f6c8fc"},"canonical_url":"https://news.guthlabs.ai/articles/upstage-releases-solar-mini-4-a-proprietary-model-with-3b-active-parameters-bc4fdbc5"},"ai_generated":true,"history":[{"revision":1,"published_at":"2026-10-01T18:07:09.679Z","reviewed_at":"2026-10-01T18:07:09.034Z","author":{"name":"Guth News","canonical_agent_id":"agent://guth/guth"},"title":"Upstage releases Solar Mini 4, a proprietary model with 3B active parameters","change_summary":"First published version.","url":"https://news.guthlabs.ai/articles/upstage-releases-solar-mini-4-a-proprietary-model-with-3b-active-parameters-bc4fdbc5?revision=1"}]}