The Known Good Updated 25 Jul 2026
IBM ·Open weights ·Released April 2026·Tracked since 25 Jul 2026

IBM: Granite 4.1 8B — quality, speed & price analysis

Compare with another model Provider benchmarks Data sources
Quality
unranked
Known Good Index
Speed
#57 of 316
94.7
Output tokens per second
Price
#30 of 340
$0.06
Blended per 1M tokens
In $0.05 · Out $0.10
Cache hit price
#68 of 206
$0.050
per 1M tokens
Context
#237 of 345
131k
tokens (~200 pages)
Summary

IBM: Granite 4.1 8B does not yet carry a Known Good Index score — the index needs at least one science, one mathematics and one coding result. It accepts text input, outputs text, and supports a 131k-token context window.

Pricing is $0.05 per 1M input tokens (below the $2.18 average) and $0.10 per 1M output (below the $9.91 average). Cached input reads at $0.050 per 1M. At 95 tokens per second it sits in the fastest quarter of the models we track.

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

Technical specifications
ReasoningNo
Input modalitytext
Output modalitytext
Context window131,072 tokens
Max output131,072 tokens
WeightsOpen weights
Knowledge cutoff
Tool callingYes
Providers1 host · compare →
Highlights — where IBM: Granite 4.1 8B sits
Price

Blended USD per 1M tokens · Lower is better · Published pricing via OpenRouter

Jump to section

Quality

How IBM: Granite 4.1 8B compares against every tracked model

Known Good IndexCoding IndexCapability indicesBy open weights
Known Good Index

Composite of GPQA Diamond, MATH / AIME, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from their publishers; we do not run these evaluations.

13 of 908 models +Add model from specific provider
💡 Reasoning models are indicated by a lightbulb
The Known Good

Quality Breakdown

IBM: Granite 4.1 8B on each evaluation feeding the index, against the tracked average

Evaluation scores

Bar = IBM: Granite 4.1 8B · grey marker = average across tracked models

None of the six index evaluations have published a score for this model yet.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Text Arena

Elo from blind pairwise votes, ingested from Arena

1422
Elo · 95% CI ±27
#107
of 381 ranked models
4k
votes counted
1307
style-controlled (#242)

Ingested 25 Jul 2026.

The Known Good

Price & Cost

Published API pricing by token type

BlendedInput vs outputCache discountQuality per dollar
Blended Price

USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better.

13 of 908 models +Add model from specific provider
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input tokens accepted

Context windowMax output tokens
Context Window

Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.

13 of 908 models +Add model from specific provider
The Known Good

Speed

Median output throughput across hosting providers

Output speedBy provider
Output Speed

Median output tokens per second across all tracked providers. Derived from OpenRouter endpoint telemetry. Higher is better.

13 of 908 models +Add model from specific provider
The Known Good

Latency

Time to first token, median across providers

Time to first tokenEnd-to-end response
Latency (TTFT)

Seconds to first streamed chunk, median across tracked providers. Derived from OpenRouter endpoint telemetry. Lower is better.

12 of 908 models +Add model from specific provider
The Known Good

Providers

Hosts serving IBM: Granite 4.1 8B, with their own price and speed

1 provider
Full provider benchmarks →
ProviderInput $/MOutput $/M BlendedSpeedTTFTContext
CoreWeave $0.05 $0.10 $0.06 112 0.2s 131k

Per-host pricing and telemetry from OpenRouter. Speed is output tokens per second; TTFT is time to first token.

The Known Good

History

How price and quality have moved since we began tracking this model

Quality & price over time

Since 25 Jul 2026

Known Good Index
Blended price $0.06 per 1M · observed 25 Jul 2026
Output speed 95 tok/s · observed 25 Jul 2026
Time to first token 0.2s

No recorded changes for this model since tracking began.

The Known Good

Comparisons

Head-to-head pages pairing IBM: Granite 4.1 8B with other tracked models

Head-to-head pages are generated for the top 50 models by Known Good Index, which IBM: Granite 4.1 8B is not currently in. Its nearest tracked models by index are below.

Browse all comparisons →
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Elo — Arena Full attribution →