UpstageReleased Apr 6, 2026
Proprietary

Solar Pro 3

Its best results are in Academic Reasoning (#160 of 223) and Knowledge Work (#135 of 186); weakest in Reliability (#158 of 188). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?
92
#167 of 186 ranked models · ahead of 10%
World (Other)'s #18 model, behind mistral-large-4 (118)
Effective cost
$0.774/1M
$0.15 in · $0.60 out
Speed
143tok/s
19s typical response
Context
128Ktokens
128,000 tokens in
Evidence
4of 7 dims
12 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract80#177 · est.● Math84#177 · est.● Academic105#160● Coding99#153● Computer Use75#174 · est.● Reliability100#158● Knowledge Work97#135
MeasuredEstimated95% range
#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10
80estimated
#177 / 221
0/5
-52.5
84estimated
#177 / 186
0/5
-65.5
105measured
#160 / 223
4/6
-30
99measured
#153 / 187
1/6
-52
75estimated
#174 / 186
0/5
-71.5
100measured
#158 / 188
3/6
-35.5
97measured
#135 / 186
4/6
-35
Solar Pro 395% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

12 of 39 Composite IQ benchmarks have a published result for Solar Pro 3. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 80 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 80 shown is estimated from Solar Pro 3's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 84 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 84 shown is estimated from Solar Pro 3's other dimensions and will be replaced as results come in. How estimates work
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 105 · measuredBest: #125 of 147 on GPQA Diamond4/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
72.4%
#125 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
10.3%
#144 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
25.5%
#160 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
0.0%
#159 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-ProMMMU-Pro
Programmatic Reasoning IQ 99 · measuredBest: #108 of 109 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 27
0.0%
#108 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 75 · estimatedNo published results0/5
No published results yet for Computer Use. The 75 shown is estimated from Solar Pro 3's other dimensions and will be replaced as results come in. How estimates work
BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 100 · measuredBest: #42 of 96 on IFBench3/6
BenchmarkScorePercentileRankLeader · source
IFBench
Artificial Analysis v4.3.2 · Oct 27
71.2%
#42 / 96
Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
32.3%
#148 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
-53.4
#153 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedBullshitBench v2FACTS Grounding
Knowledge Work IQ 97 · measuredBest: #102 of 111 on GDP.pdf4/6
BenchmarkScorePercentileRankLeader · source
GDP.pdf
Artificial Analysis v4.3.2 · Oct 27
1.6%
#102 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27
AA-Briefcase v1.1 Elo
Artificial Analysis v4.3.2 · Oct 27
99.6
#110 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 27
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 27
0.5%
#107 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v4.3.2 · Oct 27
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 20
0.0%
#123 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20
Not yet reported
AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released
Developer
Upstage
Access
Historical hosted model in the Upstage Solar API family
Weights
ProprietaryHosted access only
Inputs
text
Context
128,000 tokens
API price
$0.15 in · $0.60 outper 1M tokens · full pricing

What Upstage says

  • Solar Pro 3 is the direct proprietary predecessor to Solar Pro 4.
  • The model supports a 128k-token context window and multilingual text workloads.

Limitations

  • Solar Pro 3 is retained for historical comparison and is no longer Upstage's current flagship.

Publisher statements, not AI IQ measurements.

About this score

How much of Solar Pro 3's IQ is measured, and how the rest is estimated.

12/ 39benchmark results
4/ 7dimensions measured
3estimated
0/5Abstract
0/5Math
4/6Academic
1/6Coding
0/5Computer Use
3/6Reliability
4/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning, Mathematical Reasoning and Computer Use have no published results yet, so their IQ is estimated from Solar Pro 3's other dimensions.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare Solar Pro 3

Side-by-side pages for the models it is most often weighed against.

Solar Pro 3Comparison model
Browse all comparisons →

Frequently asked questions

Quick answers about Solar Pro 3, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →
What is the IQ of Solar Pro 3?
Solar Pro 3 has an estimated IQ of 92, which ranks #167 out of 186 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is Solar Pro 3 best at?
Among the dimensions with published benchmark results, Solar Pro 3 ranks highest in Academic Reasoning (IQ 105, #160 of 223) and Knowledge Work (IQ 97, #135 of 186). Its lowest-ranked measured dimension is Reliability (IQ 100, #158 of 188).
What is the EQ of Solar Pro 3?
Solar Pro 3 doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for Solar Pro 3. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Solar Pro 3 been tested on?
Solar Pro 3 has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, GPQA Diamond, Humanity's Last Exam, GDP.pdf and AA-Briefcase v1.1 Elo.
How much does Solar Pro 3 cost?
Solar Pro 3 costs $0.15 per million input tokens and $0.60 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.7745 per million input-plus-output tokens.
Is Solar Pro 3 open source?
No — Solar Pro 3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed Solar Pro 3?
Solar Pro 3 was developed by Upstage, based in South Korea.
When was Solar Pro 3 released?
Solar Pro 3 was publicly released on April 6, 2026.
How large is the context window of Solar Pro 3?
Solar Pro 3 supports a context window of 128,000 tokens — the amount of text it can consider in a single request.
How fast is Solar Pro 3?
In independent measurements, Solar Pro 3 generates about 143 tokens per second, with a typical response time of about 19 seconds.