gemma-2-27b: benchmark scores, price and ranking
gemma-2-27b from Google DeepMind ranks #663 of 743 LLMs on the LLMs Tiger aggregate benchmark score (43.7), based on 3 benchmark results captured up to 2026-10-14.
- Organisation
- Google DeepMind
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2024-06-24 (source: epoch)
- Cheapest API price
- $0.650 in / $0.650 out per million tokens (via openrouter, observed 2026-10-14T22:47Z)
- Aggregate rank
- #663 of 743 (score 43.7)
Relative to other models, gemma-2-27b is strongest on Epoch ECI (#120 of 204) and weakest on DTBench (#137 of 146).
Across the 3 benchmarks where at least ten models are scored, gemma-2-27b is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.650 per million tokens, is lower than that of 43% of the 427 models with a listed price.
gemma-2-27b benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 122 | #120 of 204 | Epoch AI Benchmarking Hub | 2026-10-14 |
| LMCA | 7.1% | #101 of 108 | Epoch AI Benchmarking Hub | 2026-10-14 |
| DTBench | 48.0% | #137 of 146 | Epoch AI Benchmarking Hub | 2026-10-14 |
About gemma-2-27b
gemma-2-27b is an open-weight model that can run on your own hardware from Google DeepMind. It was released on 2024-06-24, according to Epoch AI. The cheapest API listing we track charges $0.650 per million input tokens and $0.650 per million output tokens, through openrouter. We hold 3 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where gemma-2-27b stands
On our aggregate score, gemma-2-27b is #663 of 743 ranked models, in the lower half. Its score is 43.7; the scale is centred on 50, so it sits 6.3 points below the typical model. That beats 11% of the ranked field. Among the 41 ranked Google DeepMind models it is #32. The next one up is gemma-2-27b-it at 43.8. The next one down is gemma-2-9b-it at 43.0.
gemma-2-27b, benchmark by benchmark
gemma-2-27b lands below the middle on Epoch ECI: 122, #120 of 204, with 58% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Gemini 1.5 Flash (May 2024) at 123. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so gemma-2-27b is 5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
LMCA is a weak spot. gemma-2-27b scores 7.1%, #101 of 108, behind 93% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so gemma-2-27b is 22.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
DTBench is a weak spot. gemma-2-27b scores 48.0%, #137 of 146, behind 93% 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 gemma-2-27b is 20.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
Strengths and weaknesses
General knowledge and chat: weak, ahead of 24% of the field on average across 2 benchmarks. Its best board here is Epoch ECI (#120 of 204) and its weakest is LMCA (#101 of 108).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so gemma-2-27b costs more than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on gemma-2-27b-it ($0.800) and qwen2-72b-instruct ($0.900).
Release history
The Google DeepMind model released before it was Gemini 1.5 Flash (May 2024) on 2024-05-23, which scores 42.6. The next one was gemma-2-27b-it on 2024-06-24, at 43.8.
Reading these numbers
The 3 scores on this page come from 1 source: Epoch AI Benchmarking Hub (3). No official leaderboard supplied any of them, so treat them as third-party measurements. With 3 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #660 Mistral Small 3.2 (43.8)
- #661 GPT-5 nano (high) (43.8)
- #662 gemma-2-27b-it (43.8)
- #664 GPT-4 (Mar 2023) (43.7)
- #665 Magistral Small 1.2 (43.7)
- #666 Claude 2 (43.7)
More from Google DeepMind
- Gemini 3.8 Flash (high) (#28, 53.9)
- Gemini 3.7 Flash (high) (#29, 53.8)
- Gemini 3 Pro Preview (#31, 53.6)
- Gemini 3 Deep Think (#62, 52.6)
- AI co-mathematician (#71, 52.3)
- Gemini 3 Flash (#119, 51.5)
Compare it on the live leaderboard → · How the aggregate score works