Skip to content
Model Pareto

Granite 4.2 3B

IBM GraniteOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.03/M tok
Output
$0.12/M tok
Blended
$0.052/M tok · 3:1
Speed
220tok/s
Context
131Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Granite 4.2 3B. Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× B200 180GB
BF16 weights
Throughput
~16,546 tok/s
many requests batched
Price
$0.045–0.40 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, 300+ tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (3.66B params) + 25% KV-cache headroom ≈ 9 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~16,546 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~145,236 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench Pro (Public)Estimated
~#18 of 19 (estimated)~45.9%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #17Muse Glimmer51.2%
  4. ~#18Granite 4.2 3BEstimated45.9%
  5. #18Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#29 of 31 (estimated)~37.4%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #28Qwen3.8 27B42.2%
  4. ~#29Granite 4.2 3BEstimated37.4%
  5. #29Nex-N2.5-Mini36.1%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#14 of 20 (estimated)~40.8%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #13Devstral 244.8%
  4. ~#14Granite 4.2 3BEstimated40.8%
  5. #14Llama 4 Maverick39.7%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Granite 4.2 3BEstimated<41.1
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#14 of 25 (estimated)~44.1%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14Granite 4.2 3BEstimated44.1%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#55 of 116 (estimated)~34.0%
  1. #1Step 3.7 Flash98.5%
  2. #2Gemini 3.1 Pro95.6%
  3. #54Sarvam 30B34.5%
  4. ~#55Granite 4.2 3BEstimated34.0%
  5. #55Gemma 4 12B31.9%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~59.2%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Granite 4.2 3BEstimated59.2%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Granite 4.2 3BEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~51.8%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Granite 4.2 3BEstimated51.8%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks