DiffusionGemma 26B A4B
- Input
- —
- Output
- —
- Speed
- ~74tok/sest.
- Context
- 256Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: DiffusionGemma 26B A4B. Price = AA median host price.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- Hardware
- 1× B200 180GB
- BF16 weights
- Throughput
- ~10,963 tok/s
- many requests batched
- Price
- $0.062–0.56 /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 (25.2B params, 3.8B active per token) + 25% KV-cache headroom ≈ 63 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~10,963 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~139,885 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
IFBenchVerified
#58 of 13959.5%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #57K2-V260.1%
- #58DiffusionGemma 26B A4B59.5%
- #59Ternary Bonsai 27B58.5%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~#3 of 5 (estimated)~83.7%
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- ~#3DiffusionGemma 26B A4BEstimated83.7%
- #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#44 of 57 (estimated)~1382 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #43Qwen3 Next 80B A3B Instruct1386
- ~#44DiffusionGemma 26B A4BEstimated1382
- #44GLM-4.6VFew votes1361
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#43 of 57 (estimated)~1399 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #42GPT-5.4 nano1402
- ~#43DiffusionGemma 26B A4BEstimated1399
- #43Qwen3 Next 80B A3B Instruct1399
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#19 of 26 (estimated)~1588 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #18Inkling1611
- ~#19DiffusionGemma 26B A4BEstimated1588
- #19Gemini 3.5 Flash-Lite1559
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#52 of 8766.5%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #51EXAONE 4.5 33B67.3%
- #52DiffusionGemma 26B A4B66.5%
- #53GPT-5.4 nano65.4%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #11Gemini 3.5 Flash-Lite74.5%
- ~#12DiffusionGemma 26B A4BEstimated<74.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~80.7%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5DiffusionGemma 26B A4BEstimated80.7%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#35 of 48 (estimated)~8.5%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #34MiniMax-M39.8%
- ~#35DiffusionGemma 26B A4BEstimated8.5%
- #35Ling-3.0-flash-VL8.4%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #24Mistral Large 39.0%
- ~#25DiffusionGemma 26B A4BEstimated<9.0%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#122 of 19266.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #121Llama 4 Maverick67.1%
- #122DiffusionGemma 26B A4B66.9%
- #123Magistral Small 1.266.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#112 of 19810.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #112Apriel-v1.6-15B-Thinker10.8%
- #112DiffusionGemma 26B A4B10.8%
- #112Step3 VL 10B10.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~62.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23DiffusionGemma 26B A4BEstimated62.0%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#74 of 103 (estimated)~13.9
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #73Mistral Medium 3.514.2
- ~#74DiffusionGemma 26B A4BEstimated13.9
- #74Command A+13.1
No published score — estimated from related benchmarks