Models · Google (Gemini / DeepMind) · Out sinceReleased 17 Dec 2025

Gemini 3 Flash Preview

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary

Gemini 3 Flash Preview is made by Google (Gemini / DeepMind). We don't have enough test results yet to rank it. It's cheap to use.

Auto-created from OpenRouter catalog; verify details.

Writing & creativity: —
Research & analysis: —
Coding: —
Price: Cheap$0.50 / $3
Price per 1M (blended)Blended / 1M: $1.13
MemoryContext: 1M
Longest answerMax output: —
Test resultsResults: 13 (13 independent13 indep.)
Out sinceReleased: 17 Dec 2025
Made byVendor: Google (Gemini / DeepMind)
UnderstandsInputs: —

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as google/gemini-3-flash-preview.

Route it as google/gemini-3-flash-preview at $0.50 in / $3 out per 1M tokens, 1M context. Listed since 17 Dec 2025.

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
						NotesNotes
EuroEval Swedish (generative)	1.5	Defaultgemini/gemini-3-flash-preview#thinking (zero-shot, val)	Independent testIndependentEuroEval (Alexandra Institute) ↗	29 Sep 2026	—	EuroEval rank tier 3; ±0.04; lower is better; task scores (first metric): SweDN summarisation 36.34 ± 0.18, Skolprov 81.20 ± 3.14, Swedish facts 84.37 ± 1.55, ScaLA-sv 67.26 ± 1.48
LegalBench (Vals)	86.9%	Highreasoning_effort=high	Independent testIndependentVals.ai ↗	29 Sep 2026	—	vals id google/gemini-3-flash-preview; rank 10/149; ±0.356 stderr; $0.002067/test
LMArena Search Arena	1198	Defaultgemini-3-flash-grounding	Independent testIndependentLMArena ↗	24 Aug 2026	—	rank 15 (rank range 10-18); 95% CI 1193.4-1202.8; 149334 votes
ProgramBench (avg test pass rate)	31.8%	Default	Independent testIndependentProgramBench ↗	28 Sep 2026	mini-SWE-agent	avg behavioral-test pass rate ("Score" column); fully resolved 0.0%, almost (>=95% tests) 0.0%; avg cost $0.30/task
ProgramBench (fully resolved)	0.0%	Default	Independent testIndependentProgramBench ↗	28 Sep 2026	mini-SWE-agent	strict fully-resolved rate; almost (>=95% tests) 0.0%; avg cost $0.30/task
SWE Atlas - Codebase QnA	8.2%	DefaultGemini 3 Flash (Mini-SWE-Agent)	Independent testIndependentScale AI SEAL ↗	1 Oct 2026	mini-SWE-agent	rank 18 (Scale rank accounts for CI); ±3.3; entry added 2026-02-25
SWE Atlas - Refactoring	10.0%	DefaultGemini-3-Flash (Mini-SWE-Agent)	Independent testIndependentScale AI SEAL ↗	1 Oct 2026	mini-SWE-agent	rank 21 (Scale rank accounts for CI); ±4.8; entry added 2026-05-06
SWE Atlas - Test Writing	30.3%	DefaultGemini-3-Flash (Mini-SWE)	Independent testIndependentScale AI SEAL ↗	1 Oct 2026	mini-SWE-agent	rank 6 (Scale rank accounts for CI); ±5.8; entry added 2026-03-26
SWE-bench Multilingual	72.7%	Default	Independent testIndependentSWE-bench ↗	13 Feb 2026	mini-SWE-agent 2.0.0a0	Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
SWE-Bench Pro (public, v1)	34.6%	Defaultgemini-3-flash	Independent testIndependentScale AI SEAL ↗	1 Oct 2026	—	rank 14 (Scale rank accounts for CI); ±3.55; entry added 2026-01-12
SWE-bench Verified (bash-only, mini-SWE-agent)	75.8%	High	Independent testIndependentSWE-bench ↗	17 Feb 2026	mini-SWE-agent 2.0.0	Official SWE-bench bash-only (mini-SWE-agent) run; data file https://raw.githubusercontent.com/SWE-bench/swe-bench.github.io/master/data/leaderboards.json; leaderboard not updated since 2026-02-26
Vals CorpFin v2	66.4%	Highreasoning_effort=high	Independent testIndependentVals.ai ↗	12 Aug 2026	—	vals id google/gemini-3-flash-preview; rank 20/134; ±0.93 stderr; $0.047154/test
Vectara Hallucination Leaderboard (HHEM)	13.5%	Defaultgoogle/gemini-3-flash-preview	Independent testIndependentVectara ↗	22 Sep 2026	—	factual consistency 86.5 %; answer rate 99.8 %; avg summary 90.2 words; HHEM-2.3 judge; effort not stated (API default)