gemini-1.5-flash-002: benchmark scores, price and ranking
gemini-1.5-flash-002 from Google DeepMind ranks #695 of 743 LLMs on the LLMs Tiger aggregate benchmark score (42.8), based on 5 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Released
- 2024-09-24 (source: epoch)
- Aggregate rank
- #695 of 743 (score 42.8)
Relative to other models, gemini-1.5-flash-002 is strongest on OTIS Mock AIME (#133 of 189) and weakest on WeirdML (#90 of 109).
Across the 5 benchmarks where at least ten models are scored, gemini-1.5-flash-002 is in the top 10% on 0 and in the top half on 0.
gemini-1.5-flash-002 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 16.2% | #133 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 47.3% | #199 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 53.8% | #117 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| BALROG | 14.6% | #28 of 34 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 24.9% | #90 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
About gemini-1.5-flash-002
gemini-1.5-flash-002 is a smaller, lower-cost 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 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where gemini-1.5-flash-002 stands
On our aggregate score, gemini-1.5-flash-002 is #695 of 743 ranked models, in the lower half. Its score is 42.8; the scale is centred on 50, so it sits 7.2 points below the typical model. That beats 6% of the ranked field. Among the 41 ranked Google DeepMind models it is #34. The next one up is gemma-2-9b-it at 43.0. The next one down is Gemini 1.5 Flash (May 2024) at 42.6.
gemini-1.5-flash-002, benchmark by benchmark
gemini-1.5-flash-002 lands below the middle on OTIS Mock AIME: 16.2%, #133 of 189, with 70% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is gemma-3-12b-it at 16.7%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so gemini-1.5-flash-002 is 41.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-1.5-flash-002 lands below the middle on GPQA Diamond: 47.3%, #199 of 275, with 72% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is Llama-3.3-70B-Instruct at 47.4%. It covers expert-level science questions. The board median is 71.7%, so gemini-1.5-flash-002 is 24.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DTBench is a weak spot. gemini-1.5-flash-002 scores 53.8%, #117 of 146, behind 79% of the models measured. The leader, Claude Opus 5.5 (max), reaches 98.9%. It covers dynamic tool-use benchmark. The board median is 68.8%, so gemini-1.5-flash-002 is 15.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
BALROG is a weak spot. gemini-1.5-flash-002 scores 14.6%, #28 of 34, behind 79% of the models measured. The leader, GPT-6 Astra (max), reaches 68.3%. It covers long-horizon game-playing agents. The board median is 27.6%, so gemini-1.5-flash-002 is 13.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. gemini-1.5-flash-002 scores 24.9%, #90 of 109, behind 82% 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-flash-002 is 16.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: weak, ahead of 29% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#133 of 189) and its weakest is GPQA Diamond (#199 of 275). Agents and tool use: weak, ahead of 19% of the field on average across 2 benchmarks. Its best board here is DTBench (#117 of 146) and its weakest is BALROG (#28 of 34).
Release history
The Google DeepMind model released before it was gemma-2-9b-it on 2024-06-24, which scores 43.0. The next one was gemini-1.5-pro-002 on 2024-09-24, at 43.9.
Reading these numbers
The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #692 Llama-2-70b-chat-hf (42.9)
- #693 SmolLM2-1.7B (42.9)
- #694 mistral-large-2402 (42.8)
- #696 deepseek-llm-67b-chat (42.8)
- #697 Mistral Large 3 (42.7)
- #698 granite-4.0-1b (42.7)
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