Model record

Gemini 3.1 Pro Preview

Google · released Feb 19, 2026

Overall standing

Overall
56.9rank 12 of 62
56.9 is at approximately the 81th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
8 of 8 measured
Category standingsReasoning 72.2Coding 66.3Math 17.7Agentic 16.5
Reasoning
72.2rank 3 of 62
72.2 is at approximately the 96th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
66.3rank 14 of 46
66.3 is at approximately the 71th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 56.1.
2 of 2 measured
Math
17.7rank 11 of 62
17.7 is at approximately the 83th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
16.5rank 28 of 46
16.5 is at approximately the 38th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.6.
1 of 1 measured
Model factsClosed weights · $2.0 / $12.0 per 1M

Copied from the linked provider page; no separate retrieval date is stored.

Provider
Google
Released
Weights
Closed weights
Context window
1,048,576 tokens
Input price / Mtok
$2.0
Output price / Mtok
$12.0
Reasoning effort
Not listed

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 3.1 Pro Preview
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding73.8Artificial 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-BankingAgentic16.5Artificial 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-LCRReasoning72.7Artificial 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 ExamReasoning44.7Artificial 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 DiamondReasoning94.1Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding58.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning77.1Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath17.7Artificial 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)