Solar Pro4
Solar Pro4 is capable in long context; and behind the leaders in factuality, reasoning, agentic tasks, and coding. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Safety, Math, Multimodal, Multilingual or Instruction Following.
Price
$0.30input$1.20outputper million tokens
From Artificial Analysis · 2 providers tracked · All prices
Evidence
25results on22benchmarks
- 1 independently verified
- 15 aggregator
- 9 vendor-reported
From 3 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
Solar Pro4 benchmark results
25 results on 22 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
20.3% behind the leader1 of 3 ranked benchmarks measured
- 74.00Oct 8, 2026
Show 1 more long context resultHide 1 long context result
- 71.00Oct 7, 2026
25.8% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination75.60Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy18.93Oct 8, 2026omniscienceAccuracy
26.0% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond89.09Oct 8, 2026gpqa
- Humanity's Last Exam29.24Oct 8, 2026aa_hle
- 5.43Oct 8, 2026
Show 1 more reasoning resultHide 1 reasoning result
- GPQA Diamond89.00Oct 7, 2026GPQA
34.0% behind the leader4 of 7 ranked benchmarks measured
- 49.20Oct 7, 2026
- τ-Bench V3 · Banking23.30Oct 8, 2026tauBanking
- 30.49Oct 8, 2026
- Terminal-Bench 4.00.51Oct 8, 2026
36.2% behind the leader4 of 10 ranked benchmarks measured
- 70.60Oct 7, 2026
- SciCode44.56Oct 8, 2026aa_scicode
- Terminal-Bench 2.157.30Oct 8, 2026terminalbenchV21
- 1370.93Aug 13, 2026
Show 1 more coding resultHide 1 coding result
- 57.00Oct 7, 2026
0 of 5 ranked benchmarks measured
- 95.30Oct 7, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence28.15Oct 8, 2026aa_intelligence_index
- -0.85Oct 8, 2026
- Artificial Analysis Coding Index52.75Sep 9, 2026aa_coding_index
- 33.63Sep 4, 2026
- 86.30Oct 7, 2026
- τ³-Bench Banking23.00Oct 7, 2026Tau3 Banking
Show 1 more resultHide 1 result
- 87.80Aug 23, 2026
Solar Pro4: common questions
Who makes Solar Pro4?
Solar Pro4 is made by Upstage.
When was Solar Pro4 released?
Solar Pro4 was released on Aug 6, 2026, according to Artificial Analysis.
What is Solar Pro4 good at?
Solar Pro4 is capable in long context; and behind the leaders in factuality, reasoning, agentic tasks, and coding. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or instruction following.
How much does Solar Pro4 cost?
Solar Pro4 costs $0.30 per million input tokens and $1.20 per million output tokens, according to Artificial Analysis. We track its price at 2 providers. At a mix of three input tokens to one output token, it is cheaper than 59% of the 331 priced models we track.
How many benchmarks has Solar Pro4 been tested on?
We track 25 results for Solar Pro4 on 22 benchmarks from 3 sources, 1 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Solar Pro4 support?
OpenRouter lists tool calling, structured outputs, and reasoning for Solar Pro4.
About this record
Where Solar Pro4's numbers come from, and every name it appears under.
- Tracked since
- Aug 11, 2026
- Newest source mention
- Aug 13, 2026
Where the results come from
Verification: 25 scores · 1 independently verified · 15 aggregator-attributed · 9 vendor-reported. How these tiers are assigned
From 3 sources on 3 sites. Artificial Analysis supplies 15 of them; the 1 independently verified result comes from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai15
- api.llm-stats.com9
- datasets-server.huggingface.co1