Inference360
Google

Gemini 3 Flash Preview

Gemini 3 Flash Preview is a model from Google. 14 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.59.1 ±5.3
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.69/s
Input / 1MUS dollars per 1M input tokens.$0.5 batch $0.25
Output / 1MUS dollars per 1M output tokens.$3 batch $1.5 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change. Batch work costs less.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
59.3
CodingCode writing and repair.
56.4
ReasoningLogic problems and puzzles.
61.9
MultimodalTasks with images and text.
70.0
KnowledgeFacts and expert knowledge.
59.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
58.3

Results

14 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
AIMEMath95.6%58.3—16 Apr 2026Vals AI
MGSMMultilingual93.3%——9 Jan 2026Vals AI
MMLU ProKnowledge88.6%60.1—1 Sept 2026Vals AI
GPQA DiamondKnowledge87.9%59.4—1 Sept 2026Vals AI
MMMU ProMultimodal87.6%70.0—1 Sept 2026Vals AI
LiveCodeBenchCoding85.6%62.1—1 Sept 2026Vals AI
ARC-AGI-1 (semi-private)Reasoning84.7%67.2high effort—ARC Prize Foundation
SWE-bench VerifiedCoding75.8%58.3high effort · mini-SWE-agent1 Sept 2026SWE-bench team
SWE-benchCoding75.0%57.7—1 Sept 2026Vals AI
Terminal-Bench 1.0Agentic60.0%62.4—12 Jan 2026Vals AI
Terminal-Bench 2.1Agentic53.9%55.9—21 Sept 2026Vals AI
Terminal-Bench 2.0Agentic51.7%59.6—4 Jun 2026Vals AI
IOI v1Coding39.1%62.2—9 Aug 2026Vals AI
ARC-AGI-2 (semi-private)Reasoning33.6%56.7high effort—ARC Prize Foundation
Vibe Code Bench v1.1Coding20.2%50.6OpenHands21 Sept 2026Vals AI
Code MigrationCoding6.4%49.0—21 Sept 2026Vals AI
ProgramBenchCoding0.0%——21 Sept 2026Vals AI

14 benchmarks count, from 15 of 17 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial useSWE-bench team, collected directlyNo licence stated. The repository publishes submission records for reproducibility and transparency and asks that SWE-bench be cited

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Google

Gemini 3.7 Flash72.3Gemini 3.8 Flash72.1Gemini 3.5 Flash67.3Gemini 3.6 Flash66.8Gemini 3.1 Pro64.7