Google: Gemini 3.5 Flash

Google: Gemini 3.5 Flash

Google · pinned google/gemini-3.5-flash

Reproducibility

gateway_id:: google/gemini-3.5-flash
version_pinned:: google/gemini-3.5-flash
released_at:: 19 May 2026
last run:: 01 Jun 2026
temperature:: 0
top_p:: 1
seed:: unsupported
prompt_template_hash:: 5a732017979c

Score (WFT + Prompt): 32 / 40
Average of WFT and Prompt
WFT score: 32 / 40
64/80 raw
Prompt score: 31 / 40
Mean 0.764
WFT mean: 0.800
WFT stdev (sigma): 0.000
Result: Pass

Change from previous run

No earlier published WFT run yet.

Confidence interval

29.8-33.8

95% interval around 32 / 40, based on 192/240 answers.

Strong domains

WFT-Basis80% · 192/240

Weak domains

WFT-Basis80% · 192/240

Latest WFT run error types

Aggregated error categories only; no question text or raw model output.

Refusal rate: 0%
Parser errors: 0%

Type	Count	Rate
Parserfouten	0	0%
Refusals	0	0%
Timeouts	0	0%
Retry releases	0	0%
Failed jobs	2	2.5%

Score by CDFD learning objective

Objective	Correct	Total	%
WFT-Basis	192	240	80% above pass threshold

Score by advice product

Woning

88%

Rechtsbijstand

80%

Zorg

73%

Auto

70%

AVP

70%

Reis

68%

Advice product	Reviews	%
Woning	3	88% above pass threshold
Rechtsbijstand	1	80% above pass threshold
Zorg	3	73% above pass threshold
Auto	1	70% above pass threshold
AVP	1	70% above pass threshold
Reis	2	68% above pass threshold

Run history

Date	WFT score	Run
01 Jun 2026	32 / 40	combined

Model version policy

These fields show which model route, parser and dataset belong to this score.

Field	Value
Provider	Google
Gateway	google/gemini-3.5-flash
Exact API model name	google/gemini-3.5-flash
Provider release date	19 May 2026
Test date	01 Jun 2026
Endpointtype	router
Model alias or snapshot	google/gemini-3.5-flash
Provider can silently change	onbekend
Seed supported	No
Tools disabled	Yes
System prompt	Empty
Parser version