Granite 4.2 8B
by ibm-granite · Released Aug 2026
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Tested on 8 benchmarks. Top scores: Chatbot Arena Elo — Overall (1339.5%), Artificial Analysis · GPQA Diamond (64.4%), Artificial Analysis · Long Context Reasoning (49.0%).
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
- Typetext
- Context131K tokens (~66 books)
- ReleasedAug 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.000
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenKey facts · as of 2026-10-05
- Granite 4.2 8B by ibm-granite. Not enough public benchmark scores to rank yet.
- List price $0.0600 input · $0.25 output per 1M tokens (as of 2026-10-05).
- Sold by 2 providers (as of 2026-10-05): DeepInfra (bf16) $0.0600 in / $0.25 out · CoreWeave (bf16) $0.10 in / $0.15 out. Every provider
How to cite · data as of 2026-10-05
Granite 4.2 8B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/granite-4-2-8b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP