modelbench日本語

Gemini 3.1 Pro Preview

GooglePreview

Input price
$2.00
Per 1 million tokens (USD)
Output price
$12.00
Per 1 million tokens (USD)
Effort levels
3total
Default: High
Benchmark results
17total
Benchmark types: 15

Model information

API model ID
gemini-3.1-pro-preview
release date
Unknown
effort
Low / Med / High (default)
Effort source
Based on thinking level in Gemini API thinking documentation (aistudio.google.com/docs/thinking).
Claude Code
unavailable
Codex
unavailable
Availability notes
Support in Claude Code / Codex is not explicitly stated officially (Gemini API, AI Studio, Antigravity, etc. are official routes). The official model list for Claude Code / Codex (checked 2026-11-12) contains only Anthropic / OpenAI models, respectively, so both are false.
Availability source
https://aistudio.google.com/docs/models

Price (USD per 1 million tokens)

Prices do not vary by effort; token consumption does.

input$2.00
output$12.00
cache read$0.20
cache write—

Tiered pricing for ≤200k / >200k: input $2.00/$4.00, output $12.00/$18.00, cache $0.20/$0.40, storage $4.50/hr. gemini-3.1-pro-preview-customtools has the same price

Gemini 3.1 Pro Preview gemini-3.1-pro-preview $2.00 / $4.00 | $12.00 / $18.00 | $0.20 / $0.40

Source: https://aistudio.google.com/docs/pricing

Benchmark results

BenchmarkeffortScoreSource cost (metric)measured/reported bysourceConditions and extraction method
CharXiv Reasoningnot statednot stated83.3%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; without tools. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerptMultimodal | CharXiv Reasoning Information synthesis from complex charts | No tools | 83.3%Location Gemini 3.5 Flash model card Evaluation table, CharXiv Reasoning(No tools) row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, Image / CharXiv Reasoning
GPQA Diamondnot statednot stated94.1%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.transcribed from table
Source excerptgpqa_diamond.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.941, stderr=0.017, Started at=2026-02-20T05:01:02.541ZLocation gpqa_diamond.csv, data row 189 (file line 259), id=kR9F3oHBCnwQW4AiTPKwpd, Model version=gemini-3.1-pro-preview
GPQA DiamondHigh (default)High94.4%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptgpqa_diamond.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.9444444444444444, stderr=0.016319950700767385, Started at=2026-08-06T22:30:37.000ZLocation gpqa_diamond.csv, data row 128 (file line 188), id=BgmrBFsbsaD8rNpebv49Da, Model version=gemini-3.1-pro-preview_high
FrontierMath Tiers 1-3(v2)not statednot stated59.7%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tiers_1_3_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.transcribed from table
Source excerptfrontiermath_tiers_1_3_v2.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.5964912280701754, stderr=0.02911181956525014, Started at=2026-06-11T23:35:57.000ZLocation frontiermath_tiers_1_3_v2.csv, data row 110 (file line 140), id=hVifTUdQZrFEYabgCRu8Qq, Model version=gemini-3.1-pro-preview
FrontierMath Tier 4(v2)not statednot stated26.8%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, frontiermath_tier_4_v2.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.transcribed from table
Source excerptfrontiermath_tier_4_v2.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.2682926829268293, stderr=0.07005564203095158, Started at=2026-06-11T23:35:57.000ZLocation frontiermath_tier_4_v2.csv, data row 66 (file line 103), id=eXVWr3RBeSsWy5DAU8ed46, Model version=gemini-3.1-pro-preview
OTIS Mock AIME 2024-2025not statednot stated95.6%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.956, stderr=0.031, Started at=2026-02-20T04:39:36.998ZLocation otis_mock_aime_2024_2025.csv, data row 196 (file line 271), id=bXgZZgzRE3wXoSRUgrbsVf, Model version=gemini-3.1-pro-preview
OTIS Mock AIME 2024-2025High (default)High95.6%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, otis_mock_aime_2024_2025.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptotis_mock_aime_2024_2025.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.9555555555555556, stderr=0.031067790907534736, Started at=2026-08-06T23:59:11.000ZLocation otis_mock_aime_2024_2025.csv, data row 129 (file line 194), id=nhim2QCRgpir5cZdqrmUz3, Model version=gemini-3.1-pro-preview_high
SimpleQA VerifiedHigh (default)High73.5%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, simpleqa_verified.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptsimpleqa_verified.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.735, stderr=0.013963164754810065, Started at=2026-08-10T21:35:39.000ZLocation simpleqa_verified.csv, data row 99 (file line 149), id=VGeF8Xac4WcSAGgSXVdEBi, Model version=gemini-3.1-pro-preview_high
Chess Puzzles(Epoch AI)High (default)High51.0%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, chess_puzzles.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptchess_puzzles.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.51, stderr=0.05024183937956913, Started at=2026-10-13T13:34:13.000ZLocation chess_puzzles.csv, data row 123 (file line 177), id=FTDFCpXzDTgfgWBNdHLHGc, Model version=gemini-3.1-pro-preview_high
MirrorCodeHigh (default)High8.9%—Epoch AIEpoch AI, Capabilities & benchmarking (benchmark_data.zip, mirrorcode.csv) CC BY 4.0third-party · Retrieved 2026-11-12Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.transcribed from table
Source excerptmirrorcode.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.08888888888888888, stderr=0.04561939004190448, Started at=2026-08-10T16:12:46.343ZLocation mirrorcode.csv, data row 41 (file line 64), id=mirrorcode-ml-2l-gemini-3-1-pro-preview, Model version=gemini-3.1-pro-preview_high
Epoch Capabilities Index(ECI)not statednot stated156.18—Epoch AIEpoch AI, epoch_capabilities_index/eci_scores.csv (CC BY 4.0)third-party · Retrieved 2026-11-12A per-model metric that combines results across multiple benchmarks and multiple efforts (not per effort). Calculated by Epoch AI.transcribed from table
Source excerpteci_scores.csv: Model=Gemini 3.1 Pro, eci=156.18, eci_ci_low=154.39, eci_ci_high=158.14Location epoch_capabilities_index/eci_scores.csv, data row 39 (file line 40), Model=Gemini 3.1 Pro
SWE-Bench Pronot statednot stated54.2%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; average of 5 runs; internal version of the Antigravity harness; single trial. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerptSWE-Bench Pro (Public) Diverse agentic coding tasks | Single attempt | 54.2%Location Gemini 3.5 Flash model card Evaluation table, SWE-Bench Pro (Public) row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, Coding / SWE-Bench Pro
OSWorld-Verifiednot statednot stated76.2%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; average of 5 runs (1 trial each); up to 100 steps. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerptUI Control | OSWorld-Verified Agentic computer use | 76.2%Location Gemini 3.5 Flash model card Evaluation table, OSWorld-Verified row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, UI Control / OSWorld-Verified
MMMU-Pronot statednot stated80.5%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; average of Standard (10 choices) and Vision; without tools. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerptMMMU-Pro Multimodal understanding and reasoning | No tools | 80.5%Location Gemini 3.5 Flash model card Evaluation table, MMMU-Pro(No tools) row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, Image / MMMU-Pro
MRCR v2 (8-needle, 128k)not statednot stated84.9%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. All models computed in-house; cumulative score up to 128k. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerptLong context | MRCR v2 (8-needle) Long context performance | 128k (average) | 84.9%Location Gemini 3.5 Flash model card Evaluation table, MRCR v2 (8-needle) 128k (average) row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, Long Context / MRCR v2
MRCR v2 (8-needle, 1M)not statednot stated26.3%—GoogleGemini 3.5 Flash model cardofficial · Retrieved 2026-11-13Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.google/models/evals-methodology/gemini-3-5-flash): All of the results are all run with the Gemini API ... with default sampling settings unless indicated otherwise. All models computed in-house; pointwise value at 1M. Column heading is Gemini 3.1 Pro (gemini-3.1-pro-preview is the only match in the Gemini API model list). thinking level not statedtranscribed from table
Source excerpt1M (pointwise) | 26.3%Location Gemini 3.5 Flash model card Evaluation table, MRCR v2 (8-needle) 1M (pointwise) row, Gemini 3.1 Pro column. In-house computation basis: methodology PDF, Long Context / MRCR v2
τ²-bench banking_knowledge (v1.0.1)High (default)High26.0%—Sierraτ²-bench leaderboard submission gemini-3-1-pro-preview_sierra_2026-05-05 (sierra-research/tau2-bench, MIT)third-party · Retrieved 2026-11-13τ²-bench leaderboard submission gemini-3-1-pro-preview_sierra_2026-05-05 (submission_type standard, tau2_bench_version 1.0.1). Submitter "Sierra", model_organization "Google": Run by Sierra, which operates τ²-bench (third-party measurement). Verified by the leaderboard (prompts not modified, no questions omitted). Trajectories are not public (preliminary comparison). The value is pass^1 (%). reasoning_effort "high". User simulator gpt-5.2 (reasoning_effort low). Search configuration retrieval_config "alltools". Evaluation date 2026-05-05. Notes summary: rescored on 2026-07-15 following a scoring correction in v1.0.1; 4 trial runs; seed 300.transcribed from table
Source excerptbanking_knowledge.pass_1=26.03Location In submissions/gemini-3-1-pro-preview_sierra_2026-05-05/submission.json: results.banking_knowledge.pass_1 (line 22 of file). model_name "Gemini 3.1 Pro Preview". verification.details (line 39) is "Trajectories suppressed for this preliminary AllTools comparison". methodology.notes (line 35)

Related rankings

References