Skip to content
Model Pareto

Gemma 4 12B

Google DeepMindOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.10/M tok
Output
$0.30/M tok
Blended
$0.15/M tok · 3:1
Speed
118tok/s
Context
262Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Gemma 4 12B (Non-reasoning). 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
~8,514 tok/s
many requests batched
Price
$0.10–0.91 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~210 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (11.95B params) + 25% KV-cache headroom ≈ 30 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~8,514 output tok/s aggregate at batch 243 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~44,482 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.

Writing & chat

MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. #4gpt-oss-120b81.3%
  4. ~#5Gemma 4 12BEstimated<81.3%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#42 of 54 (estimated)~1359 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #41GLM-4.6VFew votes1361
  4. ~#42Gemma 4 12BEstimated1359
  5. #42Trinity Large Thinking1353
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#41 of 54 (estimated)~1378 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #40Qwen3 Next 80B A3B Instruct1399
  4. ~#41Gemma 4 12BEstimated1378
  5. #41GLM-4.6VFew votes1378
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1461 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #21Gemini 3.1 Pro1491
  4. ~#22Gemma 4 12BEstimated1461
  5. #22Mistral Large 31412
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Gemma 4 12BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~last of 9 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Gemini 3.5 Flash-Lite74.5%
  4. ~#9Gemma 4 12BEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#6 of 8 (estimated)~78.1%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #5Claude Haiku 4.579.6%
  4. ~#6Gemma 4 12BEstimated78.1%
  5. #6Mistral Small 476.4%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#33 of 43 (estimated)~5.1%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #32Qwen3.6 35B A3B6.6%
  4. ~#33Gemma 4 12BEstimated5.1%
  5. #33Claude Haiku 4.53.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 23 (estimated)below measured range (<9.0%)
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #22Mistral Large 39.0%
  4. ~#23Gemma 4 12BEstimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#14 of 25 (estimated)~56.3%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14Gemma 4 12BEstimated56.3%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#58 of 75 (estimated)~11.6
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #57Mercury 2.512.3
  4. ~#58Gemma 4 12BEstimated11.6
  5. #58gpt-oss-120b11.6
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#10 of 12 (estimated)~67.5%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #9Nex-N2.5-Mini71.2%
  4. ~#10Gemma 4 12BEstimated67.5%
  5. #10Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Gemma 4 12BEstimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#17 of 18 (estimated)~37.6%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #16Nemotron 3 Ultra44.4%
  4. ~#17Gemma 4 12BEstimated37.6%
  5. #17Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#52 of 87 (estimated)~739 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #51Mistral Medium 3.5747
  4. ~#52Gemma 4 12BEstimated739
  5. #52Ring-2.6-1T734
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#46 of 80 (estimated)~5.6%
  1. #1Claude Opus 5.569.5%
  2. #2DeepSeek V4.1 Flash68.9%
  3. #45GPT-5.4 nano6.0%
  4. ~#46Gemma 4 12BEstimated5.6%
  5. #46Qwen3.5 122B A10B5.5%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#62 of 89 (estimated)~10.1%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #61Nemotron 3 Super 120B A12B10.3%
  4. ~#62Gemma 4 12BEstimated10.1%
  5. #62Claude Haiku 4.59.3%
No published score — estimated from related benchmarks