IBM model product
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
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Granite 3.3 8B Instruct.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAlpacaEval 2.0 | Score62.68% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkAttaQ | Score88.50% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkPopQA | Score26.17% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score66.86% | Rank03 | Participants18 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkHumanEval+ | Score86.09% | Rank04 | Participants10 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score69.13% | Rank14 | Participants21 | Percentile35.00% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score89.73% | Rank14 | Participants66 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score57.56% | Rank15 | Participants26 | Percentile44.00% | EvidenceC | Evaluated |
| BenchmarkDROP | Score59.36% | Rank25 | Participants30 | Percentile17.24% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score81.20% | Rank26 | Participants53 | Percentile51.92% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score69.02% | Rank32 | Participants32 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score80.89% | Rank38 | Participants48 | Percentile21.28% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score74.82% | Rank62 | Participants68 | Percentile8.96% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score65.54% | Rank91 | Participants101 | Percentile10.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,149.30 rating | Rank207 | Participants210 | Percentile1.44% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,207.96 rating | Rank208 | Participants210 | Percentile0.96% | EvidenceA | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryindustry mathematical | Rank192 | Rating / score1,225.94 | Votes320 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank194 | Rating / score1,180.43 | Votes320 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank197 | Rating / score1,287.96 | Votes478 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank198 | Rating / score1,144.88 | Votes211 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank199 | Rating / score1,151.55 | Votes382 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank199 | Rating / score1,218.08 | Votes211 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank199 | Rating / score1,190.03 | Votes382 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank200 | Rating / score1,235.03 | Votes237 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank202 | Rating / score1,186.65 | Votes478 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank202 | Rating / score1,141.62 | Votes237 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank203 | Rating / score1,170.53 | Votes215 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank203 | Rating / score1,249.08 | Votes517 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank203 | Rating / score1,250.29 | Votes215 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank204 | Rating / score1,248.27 | Votes1,737 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank204 | Rating / score1,231.69 | Votes461 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank205 | Rating / score1,230.41 | Votes798 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank205 | Rating / score1,225.11 | Votes316 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank205 | Rating / score1,250.52 | Votes780 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank206 | Rating / score1,189.17 | Votes1,737 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank206 | Rating / score1,163.67 | Votes517 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank206 | Rating / score1,141.60 | Votes316 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank206 | Rating / score1,162.25 | Votes780 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank206 | Rating / score1,161.65 | Votes461 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank207 | Rating / score1,145.32 | Votes798 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank207 | Rating / score1,111.06 | Votes537 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank207 | Rating / score1,130.84 | Votes1,258 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank207 | Rating / score1,149.30 | Votes3,090 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank207 | Rating / score1,192.38 | Votes1,258 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank208 | Rating / score1,128.69 | Votes450 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank208 | Rating / score992.01 | Votes2,075 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
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.
Provider-specific output speed and catalog latency for Granite 3.3 8B Instruct. Runtime does not affect the capability score.
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.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGranite 3.3 8B Base | Released | LLMBoardN/A | Parameters8.2B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
| VersionGranite 3.3 8B Instruct | Released | LLMBoard2.00 | Parameters8B | Context128K | Max output8.2K | Open weightsYes | LicenseApache 2.0 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
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.
Common questions about Granite 3.3 8B.
Granite 3.3 8B's default version was released on Apr 16, 2025.
No official standard PAYG price is currently available for Granite 3.3 8B.
Granite 3.3 8B was created by IBM.
The default version has a 128K token context window.
Yes. The default version is marked as open weight under Apache 2.0.
No provider offering is currently linked to the default version.