Gemini 1.5 Pro 002
As of 8 Nov 2026, Gemini 1.5 Pro 002 by Google scores 41.4 on the BenchLeader Index (593 ranked configurations), with its best results in instruction following (55) and weakest in coding (29). Released 24 Sep 2024.
Key facts (as of 8 Nov 2026)
- Gemini 1.5 Pro 002 was released on 24 Sep 2024 (Google).
In detail. Gemini 1.5 Pro 002 is a Google model, released 24 Sep 2024. Its best configuration ranks #499 of 593 on the BenchLeader Index at 41.4 ±4.9, in the lower half. The ± is the point: 187 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (55) and lowest in coding (29). Last measured 13 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Full answer
- –
- Cost per task
- –
- Tokens per task
- –
- Released
- 24 Sep 2024
- Overall index41
- Reasoning36
- Coding29
- Maths44
- Knowledge36
- Instruction following55
Versions
Google has shipped 10 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Gemini 3.1 Pro | 19 Feb 2026 | 60.6 | #72 |
| Gemini 3 Pro | 18 Nov 2025 | 60.3 | #78 |
| Gemini 2.5 Pro | 25 Mar 2025 | 54.6 | #216 |
| Gemini 2.0 Pro | 5 Feb 2025 | 47.8 | #389 |
| Gemini 1.5 Pro 002this page | 24 Sep 2024 | 41.4 | #499 |
| Gemini 1.5 Pro | 15 May 2024 | 47.1 | #404 |
| Gemini 1.5 Pro 001 | 14 May 2024 | – | – |
| Gemini 1.0 Pro 001 | 13 Dec 2023 | – | – |
| Gemini 1.0 Pro | 6 Dec 2023 | – | – |
| Gemini 1.0 Pro 002 | – | – | – |
How its index has moved
8 Sep 2026 to 8 Nov 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source |
|---|---|---|
| GPQA Diamond | 57.2%#207 | Epoch AI Benchmarking Hub |
| Humanity's Last Exam | 4.6%#43 | Scale AI / CAIS |
| SimpleBench | 27.1%#73 | SimpleBench |
| GPQA Diamond (Vals)not in index | 58.3%#111 | Vals AI |
| GPQA Diamond (HELM)not in index | 53.4%#33 | HELM Capabilities |
| DTBenchnot in index | 59.0%#193 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| WeirdML | 22.2%#143 | WeirdML |
| LiveCodeBench | 41.7%#127 | Vals AI |
| CadEvalnot in index | 34.0%#9 | Epoch AI Benchmarking Hub |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| BALROGnot in index | 21.0%#23 | BALROG |
| TheAgentCompanynot in index | 3.4%#12 | TheAgentCompany |
| BrowseCompnot in index | 0.4%#34 | OpenAI |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| OTIS Mock AIME | 23.1%#228 | Epoch AI Benchmarking Hub |
| MATH Level 5 | 70.4%#39 | Epoch AI Benchmarking Hub |
| AIME (Vals) | 18.8%#80 | Vals AI |
| MGSM | 89.2%#48 | Vals AI |
| Omni-MATH (HELM) | 36.4%#36 | HELM Capabilities |
| MATH 500not in index | 82.8%#36 | Vals AI |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| MMLU-Pro | 75.3%#109 | Vals AI |
| LegalBench | 69.1%#127 | Vals AI |
| CorpFin | 40.5%#121 | Vals AI |
| TaxEval | 59.5%#128 | Vals AI |
| MedQA | 76.5%#75 | Vals AI |
| MMLU-Pro (HELM)not in index | 73.7%#32 | HELM Capabilities |
| MMLUnot in index | 86.9%#4 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| IFEval (HELM) | 83.7%#29 | HELM Capabilities |
| WildBench (HELM) | 81.3%#27 | HELM Capabilities |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| MMMU-Pro (Vals)not in index | 65.5%#75 | Vals AI |
| MortgageTaxnot in index | 56.8%#74 | Vals AI |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| HELM Capabilities meannot in index | 65.7%#32 | HELM Capabilities |
More from Google
See also
Embed or cite
Show where Gemini 1.5 Pro 002 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.
[](https://www.benchleader.com/models/gemini-1-5-pro-002)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 8). Gemini 1.5 Pro 002 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 8, 2026, from https://www.benchleader.com/models/gemini-1-5-pro-002
BibTeX:
@misc{benchleader_gemini_1_5_pro_002_20261108,
author = {{BenchLeader}},
title = {{Gemini 1.5 Pro 002 on the BenchLeader Index (method v1.4)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/gemini-1-5-pro-002}},
note = {Data as of 2026-11-08}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are Gemini 1.5 Pro 002's benchmark scores?
- As of 8 Nov 2026, Gemini 1.5 Pro 002 scores 41.4 ±4.9 on the BenchLeader Index, strongest in instruction following (55) and weakest in coding (29). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does Gemini 1.5 Pro 002 rank?
- Gemini 1.5 Pro 002 is #499 of 593 ranked configurations on 8 Nov 2026. 187 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 69.4.
- When was Gemini 1.5 Pro 002 released?
- Google released Gemini 1.5 Pro 002 on 24 Sep 2024.
Data as of 8 Nov 2026. Compare with another model.
Cite as: BenchLeader, “Gemini 1.5 Pro 002: benchmarks, pricing, speed and rank”, data as of 8 Nov 2026, https://www.benchleader.com/models/gemini-1-5-pro-002.