Claude Fable 5.1 vs Gemini 3.8 Flash

Gemini 3.8 Flash leads on the Visual Intelligence Index by 4.4 points, and Claude Fable 5.1 scores higher on 1 of the 7 benchmarks where the two differ.

Model

Compared with

AnthropicClaude Fable 5.176.2%Rank #3 GoogleGemini 3.8 Flash80.6%Rank #2

At a glance

Measure	Claude Fable 5.1	Gemini 3.8 Flash
Visual Intelligence Index	76.2%	80.6%
Rank	#3 of 9	#2 of 9
Cost per taskMean over the benchmarks, at list price.	$0.517	$0.0474
Latency per taskEach benchmark's median, averaged.	9.0s	25.5s
Tokens per task	51,151	60,794
Input / 1M tokens	$10.00	$0.75
Output / 1M tokens	$50.00	$3.75
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	Gemini 3.8 Flash	Lead
Perception	75.3%	79.8%	−4.5
Spatial Reasoning	77.0%	82.5%	−5.5
Temporal Reasoning	76.4%	81.3%	−5.0
Action / Event Understanding	74.0%	78.2%	−4.3
Causal Reasoning	78.7%	81.6%	−2.9
Information Retrieval	74.7%	79.4%	−4.7

Benchmarks

Benchmark	Claude Fable 5.1	Gemini 3.8 Flash	Lead
Video-MME v2	66.2%	71.3%	−5.1
LVBench	75.0%	86.4%	−11.4
Perception Test	77.3%	85.5%	−8.1
NExT-QA	86.8%	88.0%	−1.2
Q-Bench Video	71.0%	69.3%	+1.6
EgoSchema	80.4%	80.8%	−0.4
UCF101-AD	60.6%	63.5%	−2.9

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

Gemini 3.8 Flash

4.0/ 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 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
Operable1.0: Usable interactively and in bulk, not only one call at a time.
Streaming — supported
Batch API — supported