Inference
EN

Apodex 1.1 vs Apodex 1.1 Mini

Change models
Apodex 1.1Apodex
Apodex 1.1 MiniApodex
IndexAll categories, out of 100.
58.9 ±6.3 best
55.7 ±7.1
GapIndex points below the top.
Top
−3.2 · no clear gap
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-08
Input / 1MUS dollars per 1M input tokens.
—
Free
Output / 1MUS dollars per 1M output tokens.
—
Free
1K chats2K tokens in, 500 out, each.
—
Free
1K documents20K tokens in, 1K out, each.
—
Free
1K agent tasks200K tokens in, 20K out, each.
—
Free
ContextMaximum tokens in one request.
—
262K
AgenticMulti-step tasks with tools.
63.5 best
59.9
CodingCode writing and repair.
56.8 best
55.2
ReasoningLogic problems and puzzles.
53.7
53.7
MultimodalTasks with images and text.
58.2
58.2
KnowledgeFacts and expert knowledge.
57.4 best
53.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
—

Benchmarks

11 shared
Only Apodex 1.1: 7
Apodex 1.1
Apodex 1.1 Mini
Artificial Analysis Humanity's Last ExamKnowledge
34.1%65 / 222
34.1%65 / 222
Artificial Analysis Long Context ReasoningReasoning
79.3%52 / 217
79.3%52 / 217
Critical Physics TasksReasoning
4.6%87 / 214
4.6%87 / 214
Artificial Analysis GPQA DiamondKnowledge
86.4%65 / 199
86.4%65 / 199
Artificial Analysis Omniscience AccuracyKnowledge
28.2%84 / 164
28.2%84 / 164
GDPval-AA normalizedAgentic
34.4%51 / 133
34.4%51 / 133
Artificial Analysis SciCodeCoding
45.5%70 / 114
45.5%70 / 114
Artificial Analysis MMMU-ProMultimodal
79.2%27 / 113
79.2%27 / 113
APEX-Agents-AAAgentic
31.2%12 / 30
31.2%12 / 30
APEX-AgentsAgentic
38.5% best5 / 13
27.7%11 / 13
FrontierScience ResearchKnowledge
63.3%
51.7%