Skip to main content

UpstageLanguage modelActive

Solar Mini 4

Solar Mini 4 has no overall index value yet because there are too few independent benchmark results.

Intelligencenot ranked yet

n/aOverall indexhigher is better

Speednot measured

n/ano measurement yet

PriceRank 6 of 103

Input $0.10 · Output $0.40

$0.18per 1M tokenslower is better

ContextRank 68 of 112

512Ktokens in context≈ 770 A4 pages

Popularityno data yet

n/ano search or usage data

Summary

It is cheap: $0.18 per 1M tokens (input and output blended); a typical model costs $1.50.

Solar Mini 4 combines a 512K context window with an MoE model that activates just 3 of its 35 billion parameters per token. For local deployment, the provider specifies a single H100 with 80 GB of memory when using quantized weights.

The model can generate up to 128K output tokens. Upstage offers it through the Console API, Solar Chat, and OpenRouter, as well as for on-premises deployment.

Prices

Choose a price view

1 offer, prices in US dollars per 1M tokens, blended from 3 parts input and 1 part output.

ProviderInputOutputCache readBlended
Upstagedirect$0.10$0.40$0.01$0.18

Direct price according to the developer, checked Oct 25, 2026. Open the LLM price index

More price tiers and rules
Input price
US$0.10 per 1M input tokens, Upstage Console APISource
Output price
US$0.40 per 1M output tokens, Upstage Console APISource
Cache price
US$0.01 per 1M cached tokens, Upstage Console APISource
Pricing scope
Direct Upstage Console API; pricing source does not specify a region or tierSource

No subscription access recorded in Germany.

All plans in the AI subscription comparison

Solar Mini 4 in our own test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Solar Mini 4

API request failed. The model was not evaluated.

Earlier tests

The response reached the token limit. No complete recording is available.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 5, 2026 · 74 s · $0.0016

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
upstage/solar-mini4
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,192 tokens
Cost of the attempt
$0.0016
Response time
73.7 s
API model reported in response
upstage/solar-mini4
Pinned endpoint
Upstage | upstage/solar-mini4-20260922
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed
Task origin: Simon Willison

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 129 published benchmark results

Page 1 of 11

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AA-LCR: Overall (Show measurement, test conditions, and source)
Source value
83.3333333333
Metric
Pass rate
Unit
%
Benchmark version
v1.1
Category
reasoning
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 83.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-aa-lcr:v1.1:v4.3.2:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Context
This result is retained as historical evidence and is not interchangeable with current results.. This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.
Source Artificial Analysis
AutomationBench-AA: Overall (Show measurement, test conditions, and source)
Source value
22.2524256822
Metric
Objectives completed without guardrail violations
Unit
%
Benchmark version
unspecified
Category
agentic
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 22.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-automationbench-aa:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Context
This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
CritPt v2: Overall (Show measurement, test conditions, and source)
Source value
1.4285714286
Metric
pass@1 accuracy
Unit
%
Benchmark version
v2
Category
reasoning
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
disputed
Retrieved at
2026-11-02
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled. Score display: 1.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled
Context
This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
Source Artificial Analysis
CritPt: Overall (Show measurement, test conditions, and source)
Source value
1.4285714286
Metric
Score
Unit
%
Benchmark version
unspecified
Category
reasoning
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
disputed
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 1.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-critpt:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Context
Artificial Analysis marks CritPt as under review; dataset revisions may change results.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.. This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.
Source Artificial Analysis
GDP.pdf: Overall (Show measurement, test conditions, and source)
Source value
5
Metric
All-pass rate
Unit
%
Benchmark version
unspecified
Category
reasoning
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 5.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-gdp-pdf:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Context
This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
Humanity's Last Exam: Overall (Show measurement, test conditions, and source)
Source value
25.7645968489
Metric
Text-only pass@1 accuracy
Unit
%
Benchmark version
unspecified
Category
reasoning
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 25.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-humanitys-last-exam:unspecified:v4.3.2:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption.. Reasoning: reasoning enabled
Context
Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.. This result is retained as historical evidence and is not interchangeable with current results.. This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.
Source Artificial Analysis
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
Source value
18.4166666667
Metric
AA-Omniscience Accuracy
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 18.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.. This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
Source value
18.2333333333
Metric
AA-Omniscience Accuracy
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-11-02
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 18.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.. This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
AA-Omniscience Accuracy: Overall (Show measurement, test conditions, and source)
Source value
18.2333333333
Metric
AA-Omniscience Accuracy
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Higher is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
active
Retrieved at
2026-11-07
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 18.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-omniscience-accuracy:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of all questions answered correctly, regardless of whether the model answers or abstains on other questions.. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published accuracy diagnostic, not the AA-Omniscience Index. AA identifies higher values as better.
Source Artificial Analysis
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
Source value
35.8324821246
Metric
AA-Omniscience Hallucination Rate
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Lower is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-10-19
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 35.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:tokens=2000:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, source reasoning-token configuration budget=2000, suffix=not specified). This configured value is not measured token consumption. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.. This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
Source value
36.5267019976
Metric
AA-Omniscience Hallucination Rate
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Lower is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
superseded
Retrieved at
2026-11-02
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 36.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.. This result is retained as historical evidence and is not interchangeable with current results.
Source Artificial Analysis
AA-Omniscience Hallucination Rate: Overall (Show measurement, test conditions, and source)
Source value
36.5267019976
Metric
AA-Omniscience Hallucination Rate
Unit
%
Benchmark version
AA Omniscience diagnostic
Category
knowledge
Task
overall
Task label
Overall
Direction
Lower is better
Source type
independent-evaluator
Evaluator
Artificial Analysis
Status
active
Retrieved at
2026-11-07
Methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Source model ID: artificial-analysis/62ea3198-9866-4d9f-8406-a79ee78c7164/solar-mini4/solar-mini4. Source model name: Solar Mini 4. Provider reported by source: Upstage. Model snapshot: Solar Mini 4. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled. Score display: 36.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-omniscience-hallucination-rate:AA Omniscience diagnostic:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology
Exact AA configuration: Solar Mini 4 (release solar-mini4, row solar-mini4, UUID 62ea3198-9866-4d9f-8406-a79ee78c7164, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. Proportion of incorrect answers among all non-correct responses: incorrect / (incorrect + partial answers + not attempted).. Attempts: AA-reported aggregate; diagnostic-specific run count is not stated on the leaderboard. Reasoning: reasoning enabled
Context
This is the separately published hallucination-rate diagnostic, not the AA-Omniscience Index. AA identifies lower values as better.
Source Artificial Analysis

Page 1 of 11

Cost for your load

1,000 requests with 2,000 input and 500 output tokens cost $0.4000 with Solar Mini 4.

All specifications

Architecture

Model class
Mixture-of-experts language model for agents
Source: Model class
Parameters
35 billion total, 3 billion active
Source: Parameters

Input and output

Context window
512K tokens according to Upstage
Source: Context window
Maximum output
128K tokens according to Upstage
Source: Maximum output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Upstage Console API, Solar Chat, and OpenRouter
Source: Access
Shutdown
None announced
no source

API

Model ID
solar-mini4
Source: Model ID

Further details

API model version
solar-mini4-260922
Source: API model version

Frequently asked questions about Solar Mini 4

How much does Solar Mini 4 cost?

Through the API $0.10 per 1M input tokens and $0.40 output. That is cheap.

PriceDollars per 1M tokens, input and output blended · lower is better
Solar Mini 4Rank 6 of 103$0.18
MiMo V2.6 Flash$0.18
MiMo-V2.5$0.18
Muse Ember 1.0$0.20
Claude Haiku 5.5$0.20
GPT-6 Luna$0.20
GPT OSS 120B$0.20

How large is the context window of Solar Mini 4?

512,000 tokens. Separate limits may apply to input and output.

Context windowContext limit in tokens · higher is better
Solar Mini 4Rank 68 of 112512K
Solar Pro 4512K
Grok 4.7500K
Grok 4.6500K
Grok 4.5500K
GPT-5400K
GPT-5.4 mini400K

Can I run Solar Mini 4 locally?

No. Upstage does not publish the weights.

Stated by Upstage

Open weights
no
License
n/a
Parameters
35B
active per token
3B

Where can I use Solar Mini 4?

Through the API. Subscription access is not documented in the available plan data.

Through the API

$0.10 input, $0.40 output per 1M tokens.

Sources and data date

Show all 19 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

EvaluatorTest seriesComposite indicesRecorded active measurements
Artificial Analysis203

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Price

Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.

Research statusResearch date October 4, 2026. 9 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published

corrected-scicode-and-critpt-results

Note

Artificial Analysis marks SciCode and CritPt as under review following dataset audits. The checked sources do not yet publish corrected datasets and rerun results. Existing observations remain disputed and do not count as confirmed benchmark coverage.

Additional sourceUpstage Solar Mini 4 announcement (retrieved October 3, 2026; October 4, 2026; October 18, 2026) · Upstage Solar Mini 4 announcement · Editorial description reviewed October 4, 2026
Additional sourceArtificial Analysis (retrieved October 19, 2026)1234567
Additional sourceArtificial Analysis (retrieved October 16, 2026; October 19, 2026; November 2, 2026)
Additional sourceArtificial Analysis (retrieved October 19, 2026; October 29, 2026; November 2, 2026; November 7, 2026)
Additional sourceArtificial Analysis (retrieved October 19, 2026; November 2, 2026; November 7, 2026)
Additional sourceArtificial Analysis (retrieved October 16, 2026; October 19, 2026)
Additional sourcePlotly data-analytics exam for Solar Pro 4 and Solar Mini 4 (retrieved October 18, 2026)
Additional sourceDataLLM Lab (retrieved October 19, 2026)
Additional sourceArtificial Analysis (retrieved October 22, 2026)
Additional sourceDuelLab GameBench 2 model results (retrieved October 28, 2026; November 2, 2026; November 5, 2026; November 9, 2026; November 11, 2026; November 12, 2026; November 15, 2026)
Additional sourceMathBench.ai (retrieved October 28, 2026)
Additional sourceModel metadata (retrieved October 28, 2026)