Claude Fable 5.1 vs Qwen3.8-27B

Claude Fable 5.1 leads on the Visual Intelligence Index by 7.7 points, and Claude Fable 5.1 scores higher on 7 of the 7 benchmarks where the two differ.

Model

Compared with

AnthropicClaude Fable 5.176.2%Rank #3 AlibabaQwen3.8-27B68.5%Rank #6

At a glance

Measure	Claude Fable 5.1	Qwen3.8-27B
Visual Intelligence Index	76.2%	68.5%
Rank	#3 of 9	#6 of 9
Cost per taskMean over the benchmarks, at list price.	$0.517	—
Latency per taskEach benchmark's median, averaged.	9.0s	32.0s
Tokens per task	51,151	25,009
Input / 1M tokens	$10.00	—
Output / 1M tokens	$50.00	—
Context window	1M	256K
Availability	Proprietary	Open weights

How cost and latency are measured

Capabilities

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

Capability	Claude Fable 5.1	Qwen3.8-27B	Lead
Perception	75.3%	67.8%	+7.5
Spatial Reasoning	77.0%	68.6%	+8.4
Temporal Reasoning	76.4%	68.4%	+7.9
Action / Event Understanding	74.0%	65.2%	+8.8
Causal Reasoning	78.7%	72.3%	+6.4
Information Retrieval	74.7%	67.0%	+7.7

Benchmarks

Benchmark	Claude Fable 5.1	Qwen3.8-27B	Lead
Video-MME v2	66.2%	50.5%	+15.6
LVBench	75.0%	64.6%	+10.4
Perception Test	77.3%	72.3%	+5.1
NExT-QA	86.8%	82.2%	+4.6
Q-Bench Video	71.0%	67.9%	+3.1
EgoSchema	80.4%	79.1%	+1.3
UCF101-AD	60.6%	45.5%	+15.1

Usability

Claude Fable 5.1

3.0/ 5

Reachable1.0: There is an endpoint you can call without hosting anything.
First-party API — supported
Third-party API — supported
Portable0.0: You can run it yourself, and are not tied to one vendor.
Open weights — not supported
Self-hostable — not supported
Multimodal input0.0: It takes the footage directly, rather than frames you extracted.
Video ingestion — not supported
Audio — not supported
Programmable1.0: Output you can parse, and tools it can call on its own.
Structured output — supported
Tool calling — supported
Operable1.0: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — supported

Qwen3.8-27B

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