Claude Fable 5.1 vs Gemini 4 Argon

Gemini 4 Argon leads on the Visual Intelligence Index by 7.9 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 #4 GoogleGemini 4 Argon84.1%Rank #1

At a glance

Measure	Claude Fable 5.1	Gemini 4 Argon
Visual Intelligence Index	76.2%	84.1%
Rank	#4 of 10	#1 of 10
Cost per taskMean over the benchmarks, at list price.	$0.517	$0.110
Latency per taskEach benchmark's median, averaged.	9.0s	23.9s
Tokens per task	51,151	54,614
Input / 1M tokens	$10.00	$2.00
Output / 1M tokens	$50.00	$10.00
Context window	1M	1.05M
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 4 Argon	Lead
Perception	75.3%	81.7%	−6.4
Spatial Reasoning	77.0%	85.4%	−8.4
Temporal Reasoning	76.4%	84.5%	−8.1
Action / Event Understanding	74.0%	84.7%	−10.7
Causal Reasoning	78.7%	85.4%	−6.7
Information Retrieval	74.7%	82.7%	−8.0

Benchmarks

Benchmark	Claude Fable 5.1	Gemini 4 Argon	Lead
Video-MME v2	66.2%	77.0%	−10.8
LVBench	75.0%	86.3%	−11.4
Perception Test	77.3%	89.7%	−12.3
NExT-QA	86.8%	90.0%	−3.2
Q-Bench Video	71.0%	66.9%	+4.0
EgoSchema	80.4%	86.4%	−6.0
UCF101-AD	60.6%	81.8%	−21.3

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 4 Argon

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