VerdictPal
Join

Models / Other

Solar Pro 4

Solar · Released 2026-08-06

Upstage hosted Solar Pro 4. Artificial Analysis Intelligence Index 41.6. AA list $0.30 / $1.20 per 1M tokens.

Paid Solar API workhorse. Open Solar Open2 250B is the weight-release sibling. Prefer sourced ledger rows.

#50 of 166 on AA Index · current snapshot
42 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite51
ContextUnlisted
Input / 1M$0.30
Output / 1M$1.2
Knowledge cutoffunpublished
Output speed53 t/s
TTFT (default API)1.27s
Statussolid

Family profile

Best published score in each covered benchmark family.

65/100 avg
Reasoning
89
Coding
44
Agentic
57
Long context
71

4 tested benchmark families

Editor's note
Recorded from the 2026-08-15 AA snapshot (index 41.6). Not the open Solar Open2 250B weights. Editorial depth still needs a desk pass.
Benchmark placements

Where Solar Pro 4 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
τ³-Bench BankingAgentic#50/ 10623Artificial Analysis2026-09-01
GPQA DiamondReasoning#54/ 18589Artificial Analysis2026-09-01
AA time to first tokenPerformance#55/ 185Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#60/ 18442Artificial Analysis2026-09-01
AA output speedPerformance#61/ 185Artificial Analysis2026-09-01
Terminal-BenchAgentic#73/ 18457Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#80/ 18029Artificial Analysis2026-09-01
AA-LCRLong context#84/ 17971Artificial Analysis2026-09-01
SciCodeCoding#91/ 18044Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Solar Pro 4 shows up, it's highlighted.

ReasoningSolar Pro 4 · 89
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingSolar Pro 4 · 44
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticSolar Pro 4 · 57
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextSolar Pro 4 · 71
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Solar Pro 4 in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context70.67%Artificial Analysis2
AA output speedPerformance53 t/sArtificial Analysis2
AA time to first tokenPerformance1.27sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning41.6%Artificial Analysis2
GPQA DiamondReasoning89.1%Artificial Analysis2
Humanity's Last ExamReasoning29.2%Artificial Analysis2
SciCodeCoding43.6%Artificial Analysis2
τ³-Bench BankingAgentic23.3%Artificial Analysis2
Terminal-BenchAgentic57.3%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning89
Coding44
Agentic57
Long context71
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Solar Pro 4. Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Solar Pro 4.

Reasoning

Coding

Agentic

Long context

Performance

Changelog
  1. Solar Pro 4 on Artificial Analysis (index 41.6, $0.30 / $1.20).
Sources