VerdictPal
Join

Models / OpenBMB

MiniCPM-V 4.6 1.3B

MiniCPM-V 4.6 · Released 2026-05-11

AA Intelligence Index 4.2. Listed on Artificial Analysis with API pricing $0/$0 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#184 of 184 on AA Index · current snapshot
6 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite13
ContextUnlisted
Input / 1MFree
Output / 1MFree
Knowledge cutoffunpublished
Statussolid

Family profile

Best published score in each covered benchmark family.

13/100 avg
Reasoning
31
Agentic
0
Long context
7

3 tested benchmark families

Benchmark placements

Where MiniCPM-V 4.6 1.3B places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#127/ 12727Artificial Analysis2026-09-10
AA output speedPerformance#171/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#171/ 190Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#177/ 1855Artificial Analysis2026-09-10
AA-LCRLong context#179/ 1827Artificial Analysis2026-09-10
Terminal-BenchAgentic#187/ 1890Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#188/ 1886Artificial Analysis2026-09-10
GPQA DiamondReasoning#188/ 19031Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where MiniCPM-V 4.6 1.3B shows up, it's highlighted.

ReasoningMiniCPM-V 4.6 1.3B · 31
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
Long contextMiniCPM-V 4.6 1.3B · 7
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for MiniCPM-V 4.6 1.3B in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context7%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning5.7%Artificial Analysis4
GPQA DiamondReasoning30.5%Artificial Analysis4
Humanity's Last ExamReasoning5.1%Artificial Analysis4
IFBenchReasoning26.73%Artificial Analysis4
Terminal-BenchAgentic0%Artificial Analysis4
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning31
Long context7
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for MiniCPM-V 4.6 1.3B. Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for MiniCPM-V 4.6 1.3B.

Reasoning

Agentic

Long context

Performance

Sources