gemma-3-27b-it: benchmark scores, price and ranking
gemma-3-27b-it from Google DeepMind ranks #737 of 743 LLMs on the LLMs Tiger aggregate benchmark score (39.7), based on 9 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-03-12 (source: curated)
- Cheapest API price
- $0.080 in / $0.160 out per million tokens (via deepinfra, observed 2026-10-13T19:47Z)
- Aggregate rank
- #737 of 743 (score 39.7)
Relative to other models, gemma-3-27b-it is strongest on OTIS Mock AIME (#127 of 189) and weakest on Aider Polyglot (#48 of 49).
Across the 9 benchmarks where at least ten models are scored, gemma-3-27b-it is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.080 per million tokens, is lower than that of 85% of the 427 models with a listed price.
gemma-3-27b-it benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 22.5% | #127 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 47.7% | #195 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 0.0% | #92 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 52.5% | #122 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 12.3% | #91 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 0.0% | #103 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 33.3% | #44 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 21.2% | #102 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Aider Polyglot | 4.9% | #48 of 49 | Aider polyglot leaderboard | 2026-10-13 |
About gemma-3-27b-it
gemma-3-27b-it is an open-weight model that can run on your own hardware from Google DeepMind. It was released on 2025-03-12, according to the developer's announcement. The cheapest API listing we track charges $0.080 per million input tokens and $0.160 per million output tokens, through deepinfra. We hold 9 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where gemma-3-27b-it stands
On our aggregate score, gemma-3-27b-it is #737 of 743 ranked models, in the lower half. Its score is 39.7; the scale is centred on 50, so it sits 10.3 points below the typical model. That beats 1% of the ranked field. Among the 41 ranked Google DeepMind models it is #40. The next one up is gemma-3-4b-it at 39.9. The next one down is gemma-3-12b-it at 39.1.
gemma-3-27b-it, benchmark by benchmark
gemma-3-27b-it lands below the middle on OTIS Mock AIME: 22.5%, #127 of 189, with 67% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is gemini-1.5-pro-002 at 23.1%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so gemma-3-27b-it is 35.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemma-3-27b-it lands below the middle on GPQA Diamond: 47.7%, #195 of 275, with 71% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is GPT-4o (Nov 2024) at 47.9%. It covers expert-level science questions. The board median is 71.7%, so gemma-3-27b-it is 24.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemma-3-27b-it lands below the middle on CritPt: 0.0%, #92 of 115, with 79% of the field scoring higher. GPT-5.6 Sol (max) leads at 32.3%; the closest result above is gemma-3-12b-it at 0.0%. It covers unpublished research-level physics problems. The board median is 2.9%, so gemma-3-27b-it is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DTBench is a weak spot. gemma-3-27b-it scores 52.5%, #122 of 146, behind 83% 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-3-27b-it is 16.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMCA is a weak spot. gemma-3-27b-it scores 12.3%, #91 of 108, behind 83% 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-3-27b-it is 16.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Chess Puzzles is a weak spot. gemma-3-27b-it scores 0.0%, #103 of 122, behind 84% of the models measured. The leader, GPT-6 Astra (max), reaches 72.0%. It covers chess tactics puzzles. The board median is 12.5%, so gemma-3-27b-it is 12.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Fiction.liveBench is a weak spot. gemma-3-27b-it scores 33.3%, #44 of 47, behind 91% of the models measured. The leader, grok-4-0709, reaches 94.4%. It covers long-context story comprehension (16k). The board median is 61.1%, so gemma-3-27b-it is 27.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
SciCode is a weak spot. gemma-3-27b-it scores 21.2%, #102 of 106, behind 95% of the models measured. The leader, Claude Opus 5.5 (max), reaches 66.9%. It covers scientific research code. The board median is 44.3%, so gemma-3-27b-it is 23.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Aider Polyglot is a weak spot. gemma-3-27b-it scores 4.9%, #48 of 49, behind 96% of the models measured. The leader, gemini-2.5-pro-preview-06-05, reaches 83.1%. It covers edits across 6 languages (225 exercises). The board median is 44.9%, so gemma-3-27b-it is 40.0 points below it. Source: Aider polyglot leaderboard, captured 2026-10-13.
Strengths and weaknesses
Software engineering: weak, ahead of 3% of the field on average across 2 benchmarks. Its best board here is SciCode (#102 of 106) and its weakest is Aider Polyglot (#48 of 49). Reasoning, maths and science: weak, ahead of 27% of the field on average across 3 benchmarks. Its best board here is OTIS Mock AIME (#127 of 189) and its weakest is CritPt (#92 of 115). General knowledge and chat: weak, ahead of 13% of the field on average across 3 benchmarks. Its best board here is LMCA (#91 of 108) and its weakest is Fiction.liveBench (#44 of 47).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so gemma-3-27b-it 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 GPT-4.1 nano ($0.100) and Llama-3.3-70B-Instruct ($0.120).
Release history
The Google DeepMind model released before it was gemma-3-1b-it on 2025-03-12, which scores 42.4. The next one was gemma-3-4b-it on 2025-03-12, at 39.9.
Reading these numbers
The 9 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (8), Aider polyglot leaderboard (1). 1 of them come from an official leaderboard and 8 from datasets or third-party runs.
Models ranked nearby
- #734 gemma-3-4b-it (39.9)
- #735 qwen2.5-7b-instruct (39.9)
- #736 claude-3-haiku-20240307 (39.9)
- #738 Meta-Llama-3-8B-Instruct (39.4)
- #739 gemma-3-12b-it (39.1)
- #740 GPT-4.1 nano (38.7)
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