Google model product
5 Pro is a mid-size multimodal model from Google optimized for a wide range of reasoning tasks.
Updated Sep 8, 2026. Default version: Gemini 1.5 Pro
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini 1.5 Pro.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFunctionalMATH | Score64.60% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPhysicsFinals | Score63.90% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWMT23 | Score75.10% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkXSTest | Score98.80% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMRCR | Score82.60% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkNatural2Code | Score85.40% | Rank02 | Participants8 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score89.20% | Rank03 | Participants21 | Percentile90.00% | EvidenceC | Evaluated |
| BenchmarkFLEURS | Score93.30% | Rank03 | Participants6 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score93.30% | Rank03 | Participants27 | Percentile92.31% | EvidenceC | Evaluated |
| BenchmarkAMC_2022_23 | Score46.40% | Rank05 | Participants6 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkHiddenMath | Score52.00% | Rank05 | Participants13 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkVibe-Eval | Score53.90% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkVideo-MME | Score78.60% | Rank09 | Participants17 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMATH | Score86.50% | Rank10 | Participants71 | Percentile87.14% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score87.50% | Rank12 | Participants31 | Percentile63.33% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score68.10% | Rank17 | Participants39 | Percentile57.89% | EvidenceC | Evaluated |
| BenchmarkDROP | Score74.90% | Rank20 | Participants30 | Percentile34.48% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score90.80% | Rank26 | Participants48 | Percentile46.81% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score85.90% | Rank35 | Participants101 | Percentile66.00% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score84.10% | Rank39 | Participants66 | Percentile41.54% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score65.90% | Rank39 | Participants64 | Percentile39.68% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,179.37 rating | Rank73 | Participants107 | Percentile32.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,161.41 rating | Rank74 | Participants107 | Percentile31.13% | EvidenceA | Evaluated |
| BenchmarkMMLU-Pro | Score75.80% | Rank76 | Participants138 | Percentile45.26% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,350.95 rating | Rank144 | Participants210 | Percentile31.58% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,318.91 rating | Rank154 | Participants210 | Percentile26.79% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score59.10% | Rank174 | Participants247 | Percentile29.67% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorychinese | Rank63 | Rating / score1,201.26 | Votes395 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank64 | Rating / score1,185.73 | Votes395 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank73 | Rating / score1,179.37 | Votes8,902 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank74 | Rating / score1,161.41 | Votes8,902 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank76 | Rating / score1,172.03 | Votes4,829 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank79 | Rating / score1,158.78 | Votes4,829 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank109 | Rating / score1,316.33 | Votes1,210 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank111 | Rating / score1,292.45 | Votes1,210 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank111 | Rating / score1,325.25 | Votes773 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank114 | Rating / score1,357.98 | Votes8,062 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank117 | Rating / score1,297.58 | Votes773 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank119 | Rating / score1,357.80 | Votes148 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank123 | Rating / score1,332.51 | Votes8,062 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank127 | Rating / score1,353.58 | Votes14,953 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank130 | Rating / score1,336.23 | Votes9,269 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank133 | Rating / score1,290.91 | Votes148 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank134 | Rating / score1,325.89 | Votes14,953 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank136 | Rating / score1,347.69 | Votes405 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank137 | Rating / score1,309.75 | Votes405 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank138 | Rating / score1,305.13 | Votes9,269 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank138 | Rating / score1,313.40 | Votes1,281 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank139 | Rating / score1,286.10 | Votes1,281 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank139 | Rating / score1,340.92 | Votes25,473 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank139 | Rating / score1,350.19 | Votes7,738 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank140 | Rating / score1,372.31 | Votes4,444 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank141 | Rating / score1,353.75 | Votes6,506 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank142 | Rating / score1,301.21 | Votes459 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank142 | Rating / score1,339.23 | Votes22,789 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank142 | Rating / score1,357.63 | Votes8,372 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank143 | Rating / score1,312.28 | Votes35,980 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Gemini 1.5 Pro. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed85.00 tok/s | Catalog Latency0.70 s | Max Input2.1M | Max Output8.2K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 1.5 Pro | Released | LLMBoard20.09 | ParametersN/A | Context2.1M | Max output8.2K | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemini 1.5 Pro and its available data.
5 Pro is a mid-size multimodal model from Google. It can process up to 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages of text at once.
Data as of 2026-09-08.
Common questions about Gemini 1.5 Pro.
Gemini 1.5 Pro's default version was released on May 1, 2024.
No official standard PAYG price is currently available for Gemini 1.5 Pro.
Gemini 1.5 Pro was created by Google.
The default version has a 2.1M token context window.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.