Model record

Gemini 3.6 Flash

high

Google · released Jul 21, 2026

Overall standing

Overall
55.1rank 19 of 63
55.1 is at approximately the 71th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
7 of 8 measured · 1 estimated
Category standingsReasoning 68.8Coding 65.1Math 10.6Agentic 24.5
Reasoning
68.8rank 16 of 63
68.8 is at approximately the 75th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
3 of 4 measured · 1 estimated
Coding
65.1rank 18 of 63
65.1 is at approximately the 72th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
2 of 2 measured
Math
10.6rank 24 of 63
10.6 is at approximately the 63th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.7.
1 of 1 measured
Agentic
24.5rank 22 of 63
24.5 is at approximately the 66th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
1 of 1 measured
Model factsProprietary · $1.5 / $7.5 per 1M

Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.

Provider
Google
Released
Weights
Proprietary
Context window
1,048,576 tokens
Input price / Mtok
$1.5
Output price / Mtok
$7.5
Price source
Official pricing (opens in a new tab)
Reasoning effort
high reasoning

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for Gemini 3.6 Flash
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding77.5Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic24.5Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning69.7Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning38.3Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning92.8Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding52.7Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning—Not measured in this datasetNo source
CritPtMath10.6Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)