Granite 4.1 30B

IBM

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

26.5

7 benchmarks

AA Intelligence

8.9

index

Weights

Open

Released

Apr 29, 2026

About

Granite 4.1 30B is a open-weights model in the Granite family from IBM. Benchmarked on 7 evals, averaging 26.5.

Benchmark scores · 7

avg 26.5 — higher is better

GPQA Diamondartificial-analysis · 2026-07

48.1

IFBenchartificial-analysis · 2026-07

44.4

τ²-benchartificial-analysis · 2026-07

42.1

SciCodeartificial-analysis · 2026-07

25.8

AA Long-Context Reasoningartificial-analysis · 2026-07

18.7

Humanity's Last Examartificial-analysis · 2026-07

4.2

Terminal-Bench Hardartificial-analysis · 2026-07

2.3

Details

PublisherIBM

FamilyGranite

Parameters—

License—

WeightsOpen

ReleasedApr 29, 2026

Performance & price

Price in / out$0 / $0 per 1M

Coding index10.4

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0/M