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 Directory

Scoring & Data

Scoring & Data
1224 models729 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

IBM model product

Granite 3.3 8B

3 8B is an IBM large language model with enhanced reasoning, Fill-in-the-Middle code completion, and a 128K context length.

Updated Sep 8, 2026. Default version: Granite 3.3 8B Instruct

LLMBoard Score2.0Granite 3.3 8B Instruct
Coverage60%14 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Granite 3.3 8B Capability Profile

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

Granite 3.3 8B Instruct LLMBoard score breakdown

Granite 3.3 8B Benchmark Results

Benchmark scores for Granite 3.3 8B Instruct.

16 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkAlpacaEval 2.0Score62.68%Rank02Participants4Percentile66.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkAttaQScore88.50%Rank02Participants3Percentile50.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkPopQAScore26.17%Rank02Participants3Percentile50.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkTruthfulQAScore66.86%Rank03Participants18Percentile88.24%EvidenceCEvaluatedSep 8, 2026
BenchmarkHumanEval+Score86.09%Rank04Participants10Percentile66.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkBIG-Bench HardScore69.13%Rank14Participants21Percentile35.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkHumanEvalScore89.73%Rank14Participants66Percentile80.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkArena HardScore57.56%Rank15Participants26Percentile44.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkDROPScore59.36%Rank25Participants30Percentile17.24%EvidenceCEvaluatedSep 8, 2026
BenchmarkAIME 2024Score81.20%Rank26Participants53Percentile51.92%EvidenceCEvaluatedSep 8, 2026
BenchmarkMATH-500Score69.02%Rank32Participants32Percentile0.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkGSM8kScore80.89%Rank38Participants48Percentile21.28%EvidenceCEvaluatedSep 8, 2026
BenchmarkIFEvalScore74.82%Rank62Participants68Percentile8.96%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMLUScore65.54%Rank91Participants101Percentile10.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkLM Arena TextScore1,149.30 ratingRank207Participants210Percentile1.44%EvidenceAEvaluatedSep 2, 2026
BenchmarkLM Arena Text Style ControlScore1,207.96 ratingRank208Participants210Percentile0.96%EvidenceAEvaluatedSep 2, 2026

Granite 3.3 8B Arena Results

Preference and agent-evaluation results for the default version.

30 of 44 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
Arenatext style controlCategoryindustry mathematicalRank192Rating / score1,225.94Votes320ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry mathematicalRank194Rating / score1,180.43Votes320ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategorycodingRank197Rating / score1,287.96Votes478ObservationsN/AResult dateSep 2, 2026
ArenatextCategorychineseRank198Rating / score1,144.88Votes211ObservationsN/AResult dateSep 2, 2026
ArenatextCategorymathRank199Rating / score1,151.55Votes382ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategorychineseRank199Rating / score1,218.08Votes211ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategorymathRank199Rating / score1,190.03Votes382ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryexpertRank200Rating / score1,235.03Votes237ObservationsN/AResult dateSep 2, 2026
ArenatextCategorycodingRank202Rating / score1,186.65Votes478ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryexpertRank202Rating / score1,141.62Votes237ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry legal and governmentRank203Rating / score1,170.53Votes215ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryhard prompts englishRank203Rating / score1,249.08Votes517ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryindustry legal and governmentRank203Rating / score1,250.29Votes215ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryenglishRank204Rating / score1,248.27Votes1,737ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategorylonger queryRank204Rating / score1,231.69Votes461ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryhard promptsRank205Rating / score1,230.41Votes798ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryindustry business and management and financial operationsRank205Rating / score1,225.11Votes316ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryindustry software and it servicesRank205Rating / score1,250.52Votes780ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryenglishRank206Rating / score1,189.17Votes1,737ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryhard prompts englishRank206Rating / score1,163.67Votes517ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry business and management and financial operationsRank206Rating / score1,141.60Votes316ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry software and it servicesRank206Rating / score1,162.25Votes780ObservationsN/AResult dateSep 2, 2026
ArenatextCategorylonger queryRank206Rating / score1,161.65Votes461ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryhard promptsRank207Rating / score1,145.32Votes798ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryindustry entertainment and sports and mediaRank207Rating / score1,111.06Votes537ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryinstruction followingRank207Rating / score1,130.84Votes1,258ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryoverallRank207Rating / score1,149.30Votes3,090ObservationsN/AResult dateSep 2, 2026
Arenatext style controlCategoryinstruction followingRank207Rating / score1,192.38Votes1,258ObservationsN/AResult dateSep 2, 2026
ArenatextCategorycreative writingRank208Rating / score1,128.69Votes450ObservationsN/AResult dateSep 2, 2026
ArenatextCategoryexclude tiesRank208Rating / score992.01Votes2,075ObservationsN/AResult dateSep 2, 2026

Granite 3.3 8B 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.

Granite 3.3 8B Runtime Performance

Provider-specific output speed and catalog latency for Granite 3.3 8B Instruct. Runtime does not affect the capability score.

No runtime data

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

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

Granite 3.3 8B Specifications

Technical details for the model's default version.

Version
Granite 3.3 8B Instruct
Released
Apr 16, 2025
Knowledge cutoff
Apr 1, 2024
Parameters
8B
Context window
128K
Max output
8.2K
Inputs
text
Outputs
text
Open weights
Yes
License
Apache 2.0

Granite 3.3 8B Versions

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

2 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionGranite 3.3 8B BaseReleasedApr 16, 2025LLMBoardN/AParameters8.2BContextN/AMax outputN/AOpen weightsYesLicenseApache 2.0
VersionGranite 3.3 8B InstructReleasedApr 16, 2025LLMBoard2.00Parameters8BContext128KMax output8.2KOpen weightsYesLicenseApache 2.0

Models similar to Granite 3.3 8B

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

#273-2.00
IB

IBM Granite 4.0 Tiny

IBM

0.00 LLMBoard

Details
#197+22.36
IB

IBM Granite 4.2 3B

IBM

24.36 LLMBoard

Details
#176+29.61
IB

IBM Granite 4.2 8B

IBM

31.61 LLMBoard

Details
#147+37.32
IB

IBM Granite 4.2 30B

IBM

39.32 LLMBoard

Details
#265-0.04
AN

Claude Sonnet 3

Anthropic

1.96 LLMBoard

Details
#266-0.05
AC

Qwen3.5 2B

Alibaba Cloud / Qwen Team

1.95 LLMBoard

Details

What is Granite 3.3 8B?

Key information about Granite 3.3 8B and its available data.

0 license. It supports retrieval-augmented generation, function calling, response-length and originality controls, and long-context problem-solving.

Data as of 2026-09-08.

FAQ

Common questions about Granite 3.3 8B.

When was Granite 3.3 8B released?

Granite 3.3 8B's default version was released on Apr 16, 2025.

How much does Granite 3.3 8B cost?

No official standard PAYG price is currently available for Granite 3.3 8B.

Who created Granite 3.3 8B?

Granite 3.3 8B was created by IBM.

What is the context window for Granite 3.3 8B?

The default version has a 128K token context window.

Is Granite 3.3 8B open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Granite 3.3 8B?

No provider offering is currently linked to the default version.

Browse runtime rankings