Molmo 2 8B vs Qwen3.8-27B

Qwen3.8-27B leads on the Visual Intelligence Index by 10.9 points, and Molmo 2 8B scores higher on 1 of the 7 benchmarks where the two differ.

Model

Compared with

At a glance

Measure	Molmo 2 8B	Qwen3.8-27B
Visual Intelligence Index	57.6%	68.5%
Rank	#9 of 9	#6 of 9
Cost per taskMean over the benchmarks, at list price.	—	—
Latency per taskEach benchmark's median, averaged.	62.2s	32.0s
Tokens per task	12,048	25,009
Input / 1M tokens	—	—
Output / 1M tokens	—	—
Context window	37K	256K
Availability	Open weights	Open weights

Each capability index is a weighted mean of the benchmarks that contribute to the capability.

Capability	Molmo 2 8B	Qwen3.8-27B	Lead
Perception	58.7%	67.8%	−9.1
Spatial Reasoning	61.0%	68.6%	−7.6
Temporal Reasoning	57.5%	68.4%	−10.9
Action / Event Understanding	51.1%	65.2%	−14.1
Causal Reasoning	61.7%	72.3%	−10.6
Information Retrieval	52.1%	67.0%	−14.9

Benchmark	Molmo 2 8B	Qwen3.8-27B	Lead
Video-MME v2	27.5%	50.5%	−23.0
LVBench	48.6%	64.6%	−16.0
Perception Test	67.4%	72.3%	−4.8
NExT-QA	89.2%	82.2%	+7.1
Q-Bench Video	62.9%	67.9%	−5.0
EgoSchema	58.2%	79.1%	−20.9
UCF101-AD	19.5%	45.5%	−26.0

3.5/ 5

Reachable0.5: There is an endpoint you can call without hosting anything.
First-party API — supported
Third-party API — not supported
Portable1.0: You can run it yourself, and are not tied to one vendor.
Open weights — supported
Self-hostable — supported
Multimodal input0.5: It takes the footage directly, rather than frames you extracted.
Video ingestion — supported
Audio — not supported
Programmable1.0: Output you can parse, and tools it can call on its own.
Structured output — supported
Tool calling — supported
Operable0.5: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — not supported

4.5/ 5

Reachable1.0: There is an endpoint you can call without hosting anything.
First-party API — supported
Third-party API — supported
Portable1.0: You can run it yourself, and are not tied to one vendor.
Open weights — supported
Self-hostable — supported
Multimodal input1.0: It takes the footage directly, rather than frames you extracted.
Video ingestion — supported
Audio — supported
Programmable1.0: Output you can parse, and tools it can call on its own.
Structured output — supported
Tool calling — supported
Operable0.5: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — not supported