Claude Fable 5.1 vs Qwen3.8-Max

Claude Fable 5.1 leads on the Visual Intelligence Index by 2.4 points, and Claude Fable 5.1 scores higher on 4 of the 7 benchmarks where the two differ.

Model

Compared with

AnthropicClaude Fable 5.176.2%Rank #3 AlibabaQwen3.8-Max73.8%Rank #4

At a glance

Measure	Claude Fable 5.1	Qwen3.8-Max
Visual Intelligence Index	76.2%	73.8%
Rank	#3 of 9	#4 of 9
Cost per taskMean over the benchmarks, at list price.	$0.517	$0.151
Latency per taskEach benchmark's median, averaged.	9.0s	66.0s
Tokens per task	51,151	68,932
Input / 1M tokens	$10.00	$2.00
Output / 1M tokens	$50.00	$6.00
Context window	1M	1M
Availability	Proprietary	Proprietary

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-Max	Lead
Perception	75.3%	72.0%	+3.3
Spatial Reasoning	77.0%	74.3%	+2.8
Temporal Reasoning	76.4%	73.6%	+2.8
Action / Event Understanding	74.0%	71.5%	+2.4
Causal Reasoning	78.7%	78.2%	+0.5
Information Retrieval	74.7%	72.0%	+2.7

Benchmarks

Benchmark	Claude Fable 5.1	Qwen3.8-Max	Lead
Video-MME v2	66.2%	60.2%	+6.0
LVBench	75.0%	58.9%	+16.1
Perception Test	77.3%	83.9%	−6.6
NExT-QA	86.8%	87.6%	−0.8
Q-Bench Video	71.0%	69.0%	+2.0
EgoSchema	80.4%	85.2%	−4.8
UCF101-AD	60.6%	56.5%	+4.1

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-Max

3.5/ 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 input0.5: 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
Operable1.0: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — supported