Gemini 2.0 Flash (Feb 2025): benchmark scores, price and ranking
Gemini 2.0 Flash (Feb 2025) from Google DeepMind,Google ranks #537 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.1), based on 7 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind,Google
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Released
- 2025-02-05 (source: epoch)
- Cheapest API price
- $0.150 in / $0.600 out per million tokens (via vertex_ai, observed 2026-10-13T20:47Z)
- Aggregate rank
- #537 of 743 (score 46.1)
Relative to other models, Gemini 2.0 Flash (Feb 2025) is strongest on Epoch ECI (#75 of 204) and weakest on WeirdML (#88 of 109).
Across the 7 benchmarks where at least ten models are scored, Gemini 2.0 Flash (Feb 2025) is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.150 per million tokens, is lower than that of 72% of the 427 models with a listed price.
Gemini 2.0 Flash (Feb 2025) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 135 | #75 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| TheAgentCompany | 11.4% | #6 of 13 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 61.1% | #25 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 64.1% | #161 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 63.2% | #87 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 31.1% | #119 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 25.8% | #88 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Gemini 2.0 Flash (Feb 2025)
Gemini 2.0 Flash (Feb 2025) is a smaller, lower-cost model from Google DeepMind,Google. It was released on 2025-02-05, according to Epoch AI. The cheapest API listing we track charges $0.150 per million input tokens and $0.600 per million output tokens, through vertex_ai. We hold 7 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where Gemini 2.0 Flash (Feb 2025) stands
On our aggregate score, Gemini 2.0 Flash (Feb 2025) is #537 of 743 ranked models, in the lower half. Its score is 46.1; the scale is centred on 50, so it sits 3.9 points below the typical model. That beats 28% of the ranked field. Among the 5 ranked Google DeepMind,Google models it is #4. The next one up is gemini-2.0-flash-exp at 47.5. The next one down is Gemini 2.0 Flash Thinking Exp at 45.9.
Gemini 2.0 Flash (Feb 2025), benchmark by benchmark
Epoch ECI puts Gemini 2.0 Flash (Feb 2025) at 135, #75 of 204. That beats 63% of the models tested, but 22 points short of Qwen 3.8 Max (156). The results either side are Gemini 2.0 Flash (Dec 2024) (135) and Mistral Medium 3 (134). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Gemini 2.0 Flash (Feb 2025) is 7 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On TheAgentCompany, Gemini 2.0 Flash (Feb 2025) reaches 11.4%. It ranks #6 of 13, ahead of 54% of the field, and 29.7 points behind gemini-2.5-flash-preview-09-2025 at 41.1%. The results either side are Claude 3.5 Sonnet (Oct 2024) (24.0%) and GPT-4o (Nov 2024) (8.6%). It covers work tasks in a simulated software company. The board median is 8.6%, so Gemini 2.0 Flash (Feb 2025) is 2.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash (Feb 2025) lands below the middle on Fiction.liveBench: 61.1%, #25 of 47, with 51% of the field scoring higher. grok-4-0709 leads at 94.4%; the closest result above is Claude Opus 4 at 61.1%. It covers long-context story comprehension (16k). The median score on this board is also 61.1%. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash (Feb 2025) lands below the middle on GPQA Diamond: 64.1%, #161 of 275, with 58% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is DeepSeek-R1-Distill-Qwen-32B at 64.1%. It covers expert-level science questions. The board median is 71.7%, so Gemini 2.0 Flash (Feb 2025) is 7.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash (Feb 2025) lands below the middle on DTBench: 63.2%, #87 of 146, with 59% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is qwen3-14b at 64.0%. It covers dynamic tool-use benchmark. The board median is 68.8%, so Gemini 2.0 Flash (Feb 2025) is 5.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash (Feb 2025) lands below the middle on OTIS Mock AIME: 31.1%, #119 of 189, with 62% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is mistral-medium-2505 at 32.2%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Gemini 2.0 Flash (Feb 2025) is 26.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
WeirdML is a weak spot. Gemini 2.0 Flash (Feb 2025) scores 25.8%, #88 of 109, behind 80% 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 2.0 Flash (Feb 2025) is 15.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 39% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#161 of 275) and its weakest is OTIS Mock AIME (#119 of 189). Agents and tool use: uneven, ahead of 47% of the field on average across 2 benchmarks. Its best board here is TheAgentCompany (#6 of 13) and its weakest is DTBench (#87 of 146). General knowledge and chat: uneven, ahead of 43% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#75 of 204) and its weakest is WeirdML (#88 of 109).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Gemini 2.0 Flash (Feb 2025) costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Llama 4 Maverick (FP8) ($0.188) and ollama/codestral ($0.200).
Release history
The Google DeepMind,Google model released before it was gemini-2.0-flash-02-05 on 2025-02-05, which scores 48.3.
Reading these numbers
The 7 scores on this page come from 1 source: Epoch AI Benchmarking Hub (7). No official leaderboard supplied any of them, so treat them as third-party measurements. With 7 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #534 Yi-34B (46.2)
- #535 Qwen3.6 35B-A3B (46.2)
- #536 Phi-3-mini-4k-instruct (46.2)
- #538 Claude Sonnet 4 (unknown thinking) (46.1)
- #539 gemma2:27b-instruct-q8_0 (46.1)
- #540 Mathstral-7B-v0.1 (46.1)
More from Google DeepMind,Google
- gemini-exp-1206 (#176, 50.6)
- gemini-2.0-flash-02-05 (#365, 48.3)
- gemini-2.0-flash-exp (#431, 47.5)
- Gemini 2.0 Flash Thinking Exp (#549, 45.9)
Compare it on the live leaderboard → · How the aggregate score works