Solar Pro 3: Specifications & Sources

Specifications and access

Specification	Value and source
Weights	ProprietarySource
Access	APISource
Parameters	102BSource
Active parameters	12BSource
Context window	131,072 tokensSource
Notes	MoE model with 102B total parameters, 12B activated parameters per token, and a 128K context window.Source
Release	2026-01 (Month-only precision; source did not expose an exact day.)Source
Parameters	102 BSource
Architecture	MoE, 102B total / 12B activeSource
Active parameters	12 BSource
Reasoning mode	YesSource
Tool calling	YesSource

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.

Arena Hard v2 (Show measurement, test conditions, and source)

Source value: 62.5
Score: 62.5
Metric: percent
Unit: %
Category: preference
Direction: Higher is better
Source type: vendor-reported
Evaluator: official model card/release page
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor-reported; Jan 2026 release page

Source official model card/release page

IFBench (Show measurement, test conditions, and source)

Source value: 55.78
Score: 55.78
Metric: percent
Unit: %
Category: instruction
Direction: Higher is better
Source type: vendor-reported
Evaluator: official model card/release page
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor-reported; Jan 2026 release page

Source official model card/release page

SWE Bench (Show measurement, test conditions, and source)

Source value: 28.6
Score: 28.6
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: official model card/release page
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor-reported; official release page

Source official model card/release page

Terminal Bench 2 (Show measurement, test conditions, and source)

Source value: 10.1
Score: 10.1
Metric: percent
Unit: %
Category: coding
Direction: Higher is better
Source type: vendor-reported
Evaluator: official model card/release page
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor-reported; official release page

Source official model card/release page

τ²-Bench (all) (Show measurement, test conditions, and source)

Source value: 72.3
Score: 72.3
Metric: percent
Unit: %
Category: agentic
Direction: Higher is better
Source type: vendor-reported
Evaluator: official model card/release page
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. vendor-reported; official release page

Source official model card/release page

Output speed (Show measurement, test conditions, and source)

Source value: 138.178415255212
Score: 138.178415255212
Metric: tokens/s
Unit: tokens/s
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

Time per Intelligence Index Task (Show measurement, test conditions, and source)

Source value: 4.971179834391141
Score: 4.971179834391141
Metric: minutes
Unit: minutes
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

Latency reasoning time (Show measurement, test conditions, and source)

Source value: 14.474040654656887
Score: 14.474040654656887
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

Latency input time (Show measurement, test conditions, and source)

Source value: 2.49751298350009
Score: 2.49751298350009
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

Answer generation time (end-to-end timing breakdown) (Show measurement, test conditions, and source)

Source value: 3.618510163664222
Score: 3.618510163664222
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

End-to-end reasoning time component (Show measurement, test conditions, and source)

Source value: 14.474040654656887
Score: 14.474040654656887
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

End-to-end input time component (Show measurement, test conditions, and source)

Source value: 2.49751298350009
Score: 2.49751298350009
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API.

Source Artificial Analysis

Our tests

Each test shows the latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Solar Pro 3

Reasoning (requested): high

Current attempt

Run date: 2 Oct 2026
API provider: openrouter
Requested API model: upstage/solar-pro-3
API model reported in response: upstage/solar-pro-3
Reasoning setting: high
Pinned endpoint: Upstage | upstage/solar-pro-3
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 11.8 s

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

1 Oct 2026Output withheld for safetyReasoning setting: high

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

Popularity

28.6 / 100

Published prices

API input: $0.15 per 1M tokensSource
API output: $0.6 per 1M tokensSource
Cache read: $0.015 per 1M tokensSource

Predecessor and successor

Predecessor: Solar Pro 2
Model lineage evidence
Upstage calls Solar Pro 3 'the latest update to Solar Pro' and states it 'delivers meaningful gains across every category compared to Solar Pro 2' while existing Solar Pro 2 users can switch with no configuration changes.
Upstage Solar Pro 3 launch blog (2026-09-19)
Successor: Solar Pro 4
Model lineage evidence
Upstage's Solar Pro 4 post states 'Compared with Solar Pro 3, its agent capability took a major step up, and the gains are largest on evaluations that resemble real work.'.
Upstage Solar Pro 4 launch blog (2026-09-19)

Sources and data date

Type	Evidence and data date
Speed	Upstage. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Research status	Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	knowledge-cutoff Original wording No exact value located in the checked primary model card/API documentation.
Additional source	Model metadata (retrieved September 8, 2026) · Upstage Solar Pro 3 launch blog · Editorial description reviewed October 2, 2026
Additional source	Context window data · Upstage Solar Pro 3 model page · Editorial description reviewed October 2, 2026
Additional source	Upstage Solar Pro 4 launch blog · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0