llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

OpenBMB model product

MiniCPM SALA

0 checkpoint via continual training (~2T tokens, 25% of training-from-scratch cost).

Updated Aug 17, 2026. Default version: MiniCPM-SALA

Compare
LLMBoard Score21.5MiniCPM-SALA
Coverage100%10 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Compare
  • Similar models
  • About
  • FAQ

MiniCPM SALA Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

MiniCPM-SALA LLMBoard score breakdown

MiniCPM SALA Benchmark Results

Benchmark scores for MiniCPM-SALA.

24 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkHumanEvalScore95.1%Rank01Participants66Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 128K (2-needle)Score28.6%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 128K (4-needle)Score19.6%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 64K (2-needle)Score29.8%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 64K (4-needle)Score20.6%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 64K (8-needle)Score16.6%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkNoLiMa 128KScore23.9%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkNoLiMa 32KScore54.5%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkNoLiMa 64KScore43.0%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkRULER 1000KScore86.3%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkRULER 128kScore89.4%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkRULER 2048KScore81.6%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkRULER 512KScore87.1%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkRULER 64kScore92.7%Rank01Participants1Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMRCR 128K (8-needle)Score10.1%Rank02Participants2Percentile0.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkLiveCodeBench v5Score60.5%Rank04Participants9Percentile62.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkMBPPScore89.1%Rank04Participants33Percentile90.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkCMMLUScore81.5%Rank05Participants6Percentile20.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkBBHScore81.5%Rank08Participants12Percentile36.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2024Score83.8%Rank19Participants53Percentile65.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkLiveCodeBench v6Score52.0%Rank47Participants56Percentile16.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFEvalScore76.3%Rank58Participants67Percentile13.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2025Score78.3%Rank73Participants115Percentile36.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLU-ProScore67.0%Rank99Participants134Percentile26.3%EvidenceCEvaluatedAug 17, 2026

MiniCPM SALA Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

MiniCPM SALA Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No provider prices

The default version has no current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

MiniCPM SALA Runtime Performance

Provider-specific output speed and catalog latency for MiniCPM-SALA. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Browse runtime rankings

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

MiniCPM SALA Specifications

Technical details for the model's default version.

Version
MiniCPM-SALA
Released
Feb 11, 2026
Knowledge cutoff
Unknown
Parameters
9.5B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
Apache 2.0

MiniCPM SALA Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionMiniCPM-SALAReleasedFeb 11, 2026LLMBoard21.5Parameters9.5BContextN/AMax outputN/AOpen weightsNoLicenseApache 2.0

MiniCPM SALA vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

MiniCPM SALAvsQwen3 VL 4B ThinkingMiniCPM SALAvsLlama 3.3 Nemotron Super 49BMiniCPM SALAvsQwen2.5 VL 72BMiniCPM SALAvsLlama 3.3 70BMiniCPM SALAvsPhi 4 ReasoningMiniCPM SALAvsQwen2.5 72B

Models similar to MiniCPM SALA

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#195-0.0
ME

Llama 3.3 70B

Meta

21.4 LLMBoard

DetailsCompare
#196-0.2
MI

Phi 4 Reasoning

Microsoft

21.3 LLMBoard

DetailsCompare
#193+0.7
AC

Qwen2.5 VL 72B

Alibaba Cloud / Qwen Team

22.2 LLMBoard

DetailsCompare
#197-0.8
AC

Qwen2.5 72B

Alibaba Cloud / Qwen Team

20.7 LLMBoard

DetailsCompare
#192+0.8
NV

Llama 3.3 Nemotron Super 49B

NVIDIA

22.3 LLMBoard

DetailsCompare
#191+0.8
AC

Qwen3 VL 4B Thinking

Alibaba Cloud / Qwen Team

22.3 LLMBoard

DetailsCompare

What is MiniCPM SALA?

Key information about MiniCPM SALA and its available data.

0 checkpoint via continual training (~2T tokens, 25% of training-from-scratch cost). 5x inference speed over dense baselines at 256K tokens.

With HyPE (Hybrid Positional Encoding) and NoPE in sparse layers, the model extrapolates to 2048K tokens despite a 520K training length, enabling 1M-token inference on consumer GPUs like the RTX 5090.

Data as of 2026-08-17.

FAQ

Common questions about MiniCPM SALA.

When was MiniCPM SALA released?

MiniCPM SALA's default version was released on Feb 11, 2026.

How much does MiniCPM SALA cost?

No official standard PAYG price is currently available for MiniCPM SALA.

Who created MiniCPM SALA?

MiniCPM SALA was created by OpenBMB.

What is the context window for MiniCPM SALA?

A context window is not available for the default version.

Is MiniCPM SALA open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer MiniCPM SALA?

No provider offering is currently linked to the default version.

What models should I compare MiniCPM SALA with?

Nearby ranked alternatives include Qwen3 VL 4B Thinking, Llama 3.3 Nemotron Super 49B, Qwen2.5 VL 72B.