VerdictPal
Join

Models / OpenBMB

MiniCPM5-1B (Reasoning)

MiniCPM · Released 2026-06-04

OpenBMB's 1B-class reasoning model, evaluated by Artificial Analysis on 4 Jun. It belongs in the tiny-model lane, not the frontier leaderboard lane.

Tiny reasoning baseline for edge experiments, classroom comparisons, and cheap local routing tests.

#46 of 51 on AA Index · current snapshot
12 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite23
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed0 t/s
TTFT (default API)0.00s
Statuslightweight
ReasoningCodingAgenticLong context
Reasoning
49
Coding
4
Agentic
81
Long context
4

35average across 4 tested families

Benchmark placements

Where MiniCPM5-1B (Reasoning) 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
τ³-Bench BankingAgentic#10/ 6481Artificial Analysis2026-07-21
IFBenchReasoning#48/ 5749Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#59/ 657Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#61/ 6712Artificial Analysis2026-07-21
AA-LCRLong context#63/ 644Artificial Analysis2026-07-21
SciCodeCoding#65/ 654Artificial Analysis2026-07-21
AA output speedPerformance#67/ 69Artificial Analysis2026-07-21
AA time to first tokenPerformance#67/ 69Artificial Analysis2026-07-21
GPQA DiamondReasoning#69/ 6928Artificial Analysis2026-07-21
Terminal-BenchAgentic#69/ 690Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where MiniCPM5-1B (Reasoning) shows up, it's highlighted.

ReasoningMiniCPM5-1B (Reasoning) · 49
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingMiniCPM5-1B (Reasoning) · 4
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticMiniCPM5-1B (Reasoning) · 81
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextMiniCPM5-1B (Reasoning) · 4
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for MiniCPM5-1B (Reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context3.67%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning12%Artificial Analysis2
GPQA DiamondReasoning27.8%Artificial Analysis2
Humanity's Last ExamReasoning6.5%Artificial Analysis2
IFBenchReasoning49.32%Artificial Analysis2
SciCodeCoding4.4%Artificial Analysis2
τ³-Bench BankingAgentic80.99%Artificial Analysis2
Terminal-BenchAgentic0%Artificial Analysis2
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.

Reasoning49
Coding4
Agentic81
Long context4
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for MiniCPM5-1B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for MiniCPM5-1B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources