MAI-Thinking-1 vs Solar Open 2

Change models
Solar Open 2Upstage
IndexAll categories, out of 100.
52.8 ±8.1 best
52.6 ±6.2
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
70%
85% best
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-06
2026-07
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
256K
1M best
AgenticMulti-step tasks with tools.
45.3
47.3 best
CodingCode writing and repair.
54.5
55.9 best
ReasoningLogic problems and puzzles.
—
49.7
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
52.7
53.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
67.1 best
62.7
MathMath problems.
52.0
55.7 best

Benchmarks

7 shared
Only MAI-Thinking-1: 5Only Solar Open 2: 5
MAI-Thinking-1
Solar Open 2
73.5% best52 / 114
70.4%70 / 114
84.2%63 / 87
86.3% best56 / 87
85.0%19 / 73
86.2% best11 / 73
85.0% best2 / 57
80.0%12 / 57
87.7%15 / 57
92.4% best4 / 57
94.5%19 / 34
95.7% best11 / 34
84.9%17 / 27
93.9% best5 / 27