Upstage Proprietary Released Aug 6, 2026 Updated
Solar Pro 4
ToolsGuide Scores, rankings, test results and price.
Model summary
Summary
Solar Pro 4 is Upstage's model, released Aug 6, 2026. It's ranked in 3 categories and does best at text: #127 of 416, with a ToolsGuide Score of 335 against a median of 235.
It also ranks #107 of 147 for coding (259), #53 of 53 for agents (326).
It costs $0.30 per million input tokens and $1.20 per million output tokens, below the median text model ($0.43).
It has published results on 9 tests.
Specifications
- Creator
- Upstage
- Licence
- Proprietary
- Released
- Aug 6, 2026
- Context window
- 524K tokens
- Input price
- $0.30 / 1M
- Output price
- $1.20 / 1M
- Tests reported
- 9
- Settings ranked
- solar-pro4, Solar Pro 4
Model comparison
Against the ten best text models.
Text score
ToolsGuide Score out of 1,000 · Higher is better
Coding score
ToolsGuide Score out of 1,000 · Higher is better
Input price
USD per 1M input tokens · Lower is better
Leaderboards
Where Solar Pro 4 sits among the top 20 in each category.
Text
#127 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
Coding
#107 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
Agents
#53 of 53 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model
By task
Scored from votes on each kind of prompt alone, on the same 1,000-point scale.
Score against price
Text · the 10 priced models ranked closest · up and to the left is better value
Against its nearest rivals
Text prompts by kind · ToolsGuide Score from votes · hover for values
- Solar Pro 4
-
deepseek-r1-0528 -
claude-opus-4-1-20250805
Text
solar-pro4 · hover a bar for its rank
Coding
Solar Pro 4 · hover a bar for its rank
Test results
Every test Solar Pro 4 has a published result on, out of 100%, with its rank among the models that took it.
GPQA
#35 / 256Graduate-level science questions written to be hard to look up.
89.0%
Self-reported
MMLU-Pro
#13 / 142Broad knowledge and reasoning across 14 subjects, ten answer choices each.
86.3%
Self-reported
SWE-Bench Verified
#68 / 120Fixing real bugs in real GitHub projects, checked by the projects' own tests.
70.6%
Self-reported
LiveCodeBench
#5 / 76LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
87.8%
Self-reported
BrowseComp
#54 / 68Finding hard-to-locate facts by browsing the web.
49.2%
Self-reported · In the agents score
Terminal-Bench 2.1
#37 / 46Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.
57.0%
Self-reported
AIME 2026
#6 / 26All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
95.3%
Self-reported
AA-LCR
#5 / 25Agent Arena Long Context Reasoning benchmark
71.0%
Self-reported
Tau3 Banking
#6 / 13τ³-Bench banking domain evaluates agentic models on multi-turn, tool-using customer-support scenarios in a simulated retail banking environment.
23.0%
Self-reported