Skip to main content
Van Data Team

text model comparison

Granite 4.2 30B vs Muse Spark 1.3

Granite 4.2 30B and Muse Spark 1.3 are both current text models, from IBM and Meta. On Arena Text, Granite 4.2 30B scores 1340 Elo and Muse Spark 1.3 1496 Elo (Arena, measured November 9, 2026). Muse Spark 1.3 has the larger context window, 1,048,576 vs 128,000 tokens.

Higher Arena Text
Muse Spark 1.31496 Elo against 1340 Elo
Longer context window
Muse Spark 1.31.05M tokens against 128K tokens
Newer release
Muse Spark 1.3Sep 2026 against Aug 2026

Data verified November 11, 2026 · Dataset 2026-11-11

Share this

Side by side

Granite 4.2 30B and Muse Spark 1.3, line by line

Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.

FactGranite 4.2 30BMuse Spark 1.3
Price
Price per 1M input tokensNot listed$1.25
Price per 1M output tokensNot listed$4.25
Independent benchmarks
Arena Text1340 Elo (#47 of 48)1496 Elo (#6 of 48) (better)
Arena WebDevNot measured1655 Elo (#14 of 44)
FrontierMath Tiers 1-3 (v2)Not measured74.4% (#20 of 39)
Specs
ProviderIBMMeta
Release dateAugust 25, 2026September 2, 2026
Accessopen weightsAPI only
Context window128,000 tokens1,048,576 tokens
Max outputNot reportedNot reported
Inputtexttext, image, audio, video
Outputtexttext

Scores:Arena · 2026-11-11Epoch AI · 2026-11-11

Open both in the interactive comparison

Charts

Against every current text model

Where Granite 4.2 30B and Muse Spark 1.3 land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena Text, Granite 4.2 30B ranks #47 and Muse Spark 1.3 #6 of 48 current models. Each bar is the share of current models it beats: on score, price and context.

Granite 4.2 30B and Muse Spark 1.3 among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

Granite 4.2 30B:#47of 48

1,340 Elo · ahead of 2%

Muse Spark 1.3:#6of 48

1,496 Elo · ahead of 89%

Arena WebDev

Granite 4.2 30B: Not scored

Muse Spark 1.3:#14of 44

1,655 Elo · ahead of 70%

FrontierMath Tiers 1-3 (v2)

Granite 4.2 30B: Not scored

Muse Spark 1.3:#20of 39

74.4% · ahead of 50%

Price and context

Price per 1M input tokens

Granite 4.2 30B: Not listed

Muse Spark 1.3:#27of 57

$1.25 · cheaper than 50%

Price per 1M output tokens

Granite 4.2 30B: Not listed

Muse Spark 1.3:#29of 57

$4.25 · cheaper than 50%

Context window

Granite 4.2 30B:#62of 67

128K tokens · longer than 0%

Muse Spark 1.3:#12of 67

1.05M tokens · longer than 64%

Scores fromArena · 2026-11-11Epoch AI · 2026-11-11

Quality against price

Arena Text · measured November 9, 2026

Muse Spark 1.3 scores 1,496 at $2 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.

Quality against priceArena Text score against price for 40 text models, Granite 4.2 30B and Muse Spark 1.3 marked.1,2501,3001,3501,4001,4501,5001,550$0.30$1$3$10MOST ATTRACTIVE QUADRANTMedian price $2.08Median 1,472Blended price per 1M tokens (3 input : 1 output), log scaleArena Text (Elo)Muse Spark 1.3
Quality against price: the data
Arena Text score against price for 40 text models, Granite 4.2 30B and Muse Spark 1.3 marked.
ModelProviderBlended price per 1M tokensArena Text (Elo)
Gemini 4 CarbonGoogle$41,526
Gemini 4 ArgonGoogle$41,522
Muse WonderMeta$81,511
Claude Opus 5.5Anthropic$81,506
Gemini 3.8 FlashGoogle$1.501,497
Muse Spark 1.3Meta$21,496
Kimi K3Moonshot Kimi$61,487
GPT-5.6 SolOpenAI$81,485
Qwen3.8-MaxAlibaba Qwen$31,484
Gemini 3.6 FlashGoogle$31,483
GLM-5.3Z.ai$2.151,483
GPT-6.1 SolOpenAI$41,482
GPT-5.5OpenAI$111,481
MiMo-V2.6-ProXiaomi MiMo$0.541,480
GPT-5.4OpenAI$5.631,475
DeepSeek-V4.1-FlashDeepSeek$0.521,475
GPT-6 AstraOpenAI$201,474
GLM-5.3-FlashZ.ai$0.241,474
Gemini 3 Flash PreviewGoogle$1.131,473
Grok 4.20xAI$1.561,472
Claude Sonnet 5.5Anthropic$41,472
GPT-5.6 TerraOpenAI$4.501,468
Grok 4.5xAI$31,466
DeepSeek-V4-ProDeepSeek$1.981,464
GPT-6 SolOpenAI$41,457
Grok 4.6xAI$31,456
Gemini 3.5 Flash-LiteGoogle$0.851,455
GPT-5.6 LunaOpenAI$0.451,453
MiMo-V2.6-FlashXiaomi MiMo$0.181,448
Step 5 PreviewStepFun$1.431,448
Grok 4.3xAI$1.561,442
Grok 4.7xAI$31,442
GPT-6 LunaOpenAI$0.201,441
Mistral Large 4Mistral AI$1.051,423
Claude Haiku 5.5Anthropic$0.201,422
GPT-4.1OpenAI$3.501,415
Inkling 2 SmallThinking Machines Lab$0.471,412
Solar Pro 4Upstage$0.521,387
GPT-4.1 miniOpenAI$0.701,383
GPT-4.1 nanoOpenAI$0.181,322

Cost

What each costs

Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.

Workload or rateGranite 4.2 30BMuse Spark 1.3
Other listed rates
1M input tokens, cachedNot listed$0.15

Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.

Launch price $100, regular price $150

Book the cost audit

Verdict

When to choose each

Granite 4.2 30B

Where it leads

  • Open weights you can run yourself

Best for

  • Self-hosted enterprise agents that need a permissive licence

Watch out for

  • IBM says it is fine-tuned mainly on English instruction data, so other languages may be weaker
  • IBM publishes no per-token API price for Granite 4.2
Full Granite 4.2 30B profile

Muse Spark 1.3

Where it leads

  • Higher Arena Text score, 1496 Elo vs 1340 Elo
  • Larger context window 1,048,576 vs 128,000 tokens
  • Accepts image, audio and video input
  • A cached-input rate, $0.15 per 1M tokens

Best for

  • Tool-heavy agent loops where fewer calls per task matters as much as the per-token rate
  • Coding agents at volume, where its coding scores and low price line up

Watch out for

  • Meta’s own documentation states audio understanding is not fully supported and response quality may be degraded on requests containing audio
  • The much cheaper contributor endpoint (about $0.10 / $0.20 per million) is priced that way in exchange for Meta training on your traffic. The standard tier is the rate recorded here.
  • Meta’s scorecard has it trailing Claude Opus 5 on every broader agent-workflow benchmark it published, including GDPVal-AA v2, despite winning the coding rows
Full Muse Spark 1.3 profile

From benchmark to production

Building on Granite 4.2 30B or Muse Spark 1.3?

Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.

AI Model Cost AuditLaunch price $100, regular price $150What the audit includes

Book the cost auditAI agent development

FAQ

Granite 4.2 30B vs Muse Spark 1.3 FAQ

Do Granite 4.2 30B and Muse Spark 1.3 discount cached input?

Muse Spark 1.3 lists a cached-input rate of $0.15 per 1M tokens, 88% below its standard input rate. No cached-input rate is listed for Granite 4.2 30B.

Which scores higher on independent benchmarks, Granite 4.2 30B or Muse Spark 1.3?

Muse Spark 1.3 leads on Arena Text, 1496 Elo to 1340 Elo. Scores are independent evaluations, not either vendor's launch figures.

Which has the larger context window, Granite 4.2 30B or Muse Spark 1.3?

Muse Spark 1.3 has the larger context window, 1,048,576 vs 128,000 tokens.

How do Granite 4.2 30B and Muse Spark 1.3 differ in features?

Granite 4.2 30B takes text input; Muse Spark 1.3 takes text, image, audio and video.

Can I run Granite 4.2 30B or Muse Spark 1.3 myself?

Granite 4.2 30B is released as open weights you can run yourself; Muse Spark 1.3 is available through its provider's API only.

Further reading

More on Granite 4.2 30B and Muse Spark 1.3

Related comparisons

Production evaluation

Choosing between Granite 4.2 30B and Muse Spark 1.3?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty
Compare all modelsBook a consultation