Solar Pro 2 (Reasoning)

Solar Pro 2 (Reasoning)

Upstage · Released Jul 9, 2025 Emerging
Intelligence #411 / 544
22.7 Our Score
AA Index #225 / 365
14.9 Artificial Analysis
Input
Not priced
Output
Not priced
Context
Not reported

Analysis Summary

Solar Pro 2 (Reasoning) sits in the Emerging tier on our leaderboard, ranked #411 of 544 published models on overall intelligence. At $0.000 input and $0.000 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

Solar Pro 2 (Reasoning) from Upstage shows strong math and livecodebench scores for its size, but a low intelligence index and limited agentic capability cap its usefulness for professional workflows.

Assessed May 5, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.5Technical2.3Value0Content3.5
Intelligence 3.5/10
Technical 2.3/10
Content 3.5/10
Value 0/10

Performance Indices

Source: Artificial Analysis

14.9 Intelligence Index
12.1 Coding Index
15.6 Agentic Index
61.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 68.7% Graduate-level scientific reasoning
HLE 7% Humanity's Last Exam
MMLU Pro 80.5% Multi-task language understanding
MATH 500 96.7% Mathematical problem-solving
AIME 69% Competition mathematics
AIME 2025 61.3% Competition mathematics (2025)
SciCode 30.2% Scientific computing

Technical

LiveCodeBench 61.6% Live coding evaluation
TerminalBench Hard 3% Agentic terminal tasks
τ²-Bench 28.1% Conversational agent benchmark

Content

IFBench 37.1% Instruction following

Benchmark data from Artificial Analysis and Hugging Face

How does Solar Pro 2 (Reasoning) stack up?

Compare side-by-side with other emerging models.

Compare Models

Model Information

ProviderUpstage
Release Date July 9, 2025
Status Active