Molmo 7B-D
- Input
- —
- Output
- —
- Speed
- ~98tok/sest.
- Context
- 4Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Molmo 7B-D. Price = AA median host price.
Rankings
Writing & chat
Verified#157 / 162rank by quality10.3±9.5quality / 1001/5 benchmarks measuredVision
Verified#97 / 98rank by quality10.4±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#217 / 218rank by quality6.0±5.9quality / 1002/4 benchmarks measuredAgents
Verified#185 / 187rank by quality10.2±10.0quality / 1001/7 benchmarks measured
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
- ~10,746 tok/s
- many requests batched
- Price
- $0.077–0.68 /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 (8.02B params) + 25% KV-cache headroom ≈ 20 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~10,746 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~66,280 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
#136 of 13919.7%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #135Tiny Aya Global20.1%
- #136Molmo 7B-D19.7%
- #137Granite 4.0 H 350M17.6%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#55 of 57 (estimated)~1266 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #54NVIDIA Nemotron 3 Nano 30B A3B1286
- ~#55Molmo 7B-DEstimated1266
- #55Phi-41233
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#55 of 57 (estimated)~1296 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #54NVIDIA Nemotron 3 Nano 30B A3B1314
- ~#55Molmo 7B-DEstimated1296
- #55Olmo 3.1 32B Think1286
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1348 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24Molmo 7B-DEstimated1348
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#86 of 8724.5%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #85Qwen3.5 0.8B25.7%
- #86Molmo 7B-D24.5%
- #87Phi-4 Multimodal Instruct14.5%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#46 of 48 (estimated)~0.1%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #45Ministral 3 8B0.8%
- ~#46Molmo 7B-DEstimated0.1%
- #46Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#189 of 19224.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #188Apertus 8B Instruct25.6%
- #189Molmo 7B-D24.0%
- #190Qwen3.5 0.8B23.6%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#158 of 1985.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #158MiniCPM-V 4.6 1.3B5.1%
- #158Molmo 7B-D5.1%
- #158Qwen3.5 0.8B5.1%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#31 of 34 (estimated)~18.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #30Llama 4 Maverick19.3%
- ~#31Molmo 7B-DEstimated18.4%
- #31Falcon-H1-34B-Instruct16.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#102 of 103 (estimated)~3.9
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #100NVIDIA Nemotron 3 Nano 4B4.8
- ~#102Molmo 7B-DEstimated3.9
- #102K2 Horizon 0.9B3.0
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#110 of 1190.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #110Kimi Linear 48B A3B Instruct0.0%
- #110Molmo 7B-D0.0%
- #110Molmo2-8B0.0%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#14 of 15 (estimated)~50.8%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #13Nemotron 3.5 Super VL51.1%
- ~#14Molmo 7B-DEstimated50.8%
- #14Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~33.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Molmo 7B-DEstimated33.8%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#62 of 92 (estimated)~614 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #61Nemotron 3.5 Lightning624
- ~#62Molmo 7B-DEstimated614
- #62Gemma 4 31B606
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#85 of 85 (estimated)~0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~last of 91 (estimated)below measured range (<3.3%)
No published score — estimated from related benchmarks