gemini-1.5-pro-002: benchmark scores, price and ranking
gemini-1.5-pro-002 from Google DeepMind ranks #660 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.9), based on 9 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Frontier model
- Open weights
- No
- Released
- 2024-09-24 (source: epoch)
- Aggregate rank
- #660 of 743 (score 43.9)
Relative to other models, gemini-1.5-pro-002 is strongest on Aider Code Editing (#25 of 92) and weakest on WeirdML (#93 of 109).
Across the 9 benchmarks where at least ten models are scored, gemini-1.5-pro-002 is in the top 10% on 0 and in the top half on 1.
gemini-1.5-pro-002 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Aider Code Editing | 65.4% | #25 of 92 | Aider Aider Code Editing leaderboard | 2026-10-13 |
| BALROG | 21.0% | #20 of 34 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 57.2% | #170 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 23.1% | #126 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 59.0% | #107 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 27.1% | #47 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Humanity's Last Exam | 4.6% | #22 of 27 | Epoch AI Benchmarking Hub | 2026-10-13 |
| TheAgentCompany | 3.4% | #11 of 13 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 22.2% | #93 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
About gemini-1.5-pro-002
gemini-1.5-pro-002 is a frontier model from Google DeepMind. It was released on 2024-09-24, according to Epoch AI. No API price is listed for it yet. We hold 9 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where gemini-1.5-pro-002 stands
On our aggregate score, gemini-1.5-pro-002 is #660 of 743 ranked models, in the lower half. Its score is 43.9; the scale is centred on 50, so it sits 6.1 points below the typical model. That beats 11% of the ranked field. Among the 41 ranked Google DeepMind models it is #30. The next one up is gemini-1.5-pro-001 at 44.0. The next one down is gemma-2-27b-it at 43.8.
gemini-1.5-pro-002, benchmark by benchmark
Aider Code Editing puts gemini-1.5-pro-002 at 65.4%, #25 of 92. That beats 73% of the models tested, but 18.8 points short of Claude 3.5-Sonnet-20241022 (84.2%). The results either side are Llama-3.1-405B-Instruct (66.2%) and gpt-4-1106-preview (65.4%). It covers Aider official benchmark. The board median is 55.6%, so gemini-1.5-pro-002 is 9.8 points above it. Source: Aider Aider Code Editing leaderboard, captured 2026-10-13.
gemini-1.5-pro-002 lands below the middle on BALROG: 21.0%, #20 of 34, with 56% of the field scoring higher. GPT-6 Astra (max) leads at 68.3%; the closest result above is Llama-3.3-70B-Instruct at 23.0%. It covers long-horizon game-playing agents. The board median is 27.6%, so gemini-1.5-pro-002 is 6.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-1.5-pro-002 lands below the middle on GPQA Diamond: 57.2%, #170 of 275, with 61% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is Mellum2-12B-A2.5B-Thinking at 57.6%. It covers expert-level science questions. The board median is 71.7%, so gemini-1.5-pro-002 is 14.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-1.5-pro-002 lands below the middle on OTIS Mock AIME: 23.1%, #126 of 189, with 66% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is Magistral Small 1.2 at 28.1%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so gemini-1.5-pro-002 is 34.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-1.5-pro-002 lands below the middle on DTBench: 59.0%, #107 of 146, with 73% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is Llama-3.3-70B-Instruct at 59.5%. It covers dynamic tool-use benchmark. The board median is 68.8%, so gemini-1.5-pro-002 is 9.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-1.5-pro-002 lands below the middle on SimpleBench: 27.1%, #47 of 61, with 75% of the field scoring higher. Claude Fable 5 (max) leads at 81.9%; the closest result above is DeepSeek-V3 (Mar 2025) at 27.2%. It covers trick questions that test common sense. The board median is 41.4%, so gemini-1.5-pro-002 is 14.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Humanity's Last Exam is a weak spot. gemini-1.5-pro-002 scores 4.6%, #22 of 27, behind 78% of the models measured. The leader, Muse Spark, reaches 40.6%. It covers expert-level questions across domains. The board median is 10.7%, so gemini-1.5-pro-002 is 6.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
TheAgentCompany is a weak spot. gemini-1.5-pro-002 scores 3.4%, #11 of 13, behind 77% of the models measured. The leader, gemini-2.5-flash-preview-09-2025, reaches 41.1%. It covers work tasks in a simulated software company. The board median is 8.6%, so gemini-1.5-pro-002 is 5.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. gemini-1.5-pro-002 scores 22.2%, #93 of 109, behind 84% of the models measured. The leader, GPT-6 Astra (max), reaches 93.3%. It covers unusual machine-learning tasks. The board median is 41.2%, so gemini-1.5-pro-002 is 19.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 28% of the field on average across 4 benchmarks. Its best board here is GPQA Diamond (#170 of 275) and its weakest is Humanity's Last Exam (#22 of 27). Agents and tool use: weak, ahead of 28% of the field on average across 3 benchmarks. Its best board here is BALROG (#20 of 34) and its weakest is TheAgentCompany (#11 of 13).
Release history
The Google DeepMind model released before it was gemini-1.5-flash-002 on 2024-09-24, which scores 42.8. The next one was gemini-1.5-flash-8b-001 on 2024-10-03, at 42.0.
Reading these numbers
The 9 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (8), Aider Aider Code Editing leaderboard (1). 1 of them come from an official leaderboard and 8 from datasets or third-party runs.
Models ranked nearby
- #657 qwen2-72b-instruct (43.9)
- #658 ollama/hermes3 (43.9)
- #659 Qwen2-7B (43.9)
- #661 GPT-5 nano (high) (43.8)
- #662 gemma-2-27b-it (43.8)
- #663 Magistral Small 1.2 (43.8)
More from Google DeepMind
- Gemini 3.8 Flash (high) (#26, 54.0)
- Gemini 3.7 Flash (high) (#27, 53.9)
- Gemini 3 Pro Preview (#31, 53.7)
- Gemini 3 Deep Think (#60, 52.6)
- AI co-mathematician (#69, 52.3)
- Gemini 3 Flash (#120, 51.5)
Compare it on the live leaderboard → · How the aggregate score works