Compare · ModelsLive · 2 picked · head to head
Gemma 3 27B (free) vs GPT-4.1 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-4.1 Mini wins on 5/5 benchmarks
GPT-4.1 Mini wins 5 of 5 shared benchmarks. Leads in coding · knowledge · math.
Category leads
coding·GPT-4.1 Miniknowledge·GPT-4.1 Minimath·GPT-4.1 Mini
Hype vs Reality
Attention vs performance
Gemma 3 27B (free)
#172 by perf·#7 by attention
GPT-4.1 Mini
#211 by perf·no signal
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
5 benchmarks · 2 models
Gemma 3 27B (free)GPT-4.1 Mini
Aider polyglot
GPT-4.1 Mini leads by +27.5
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
Gemma 3 27B (free)
4.9
GPT-4.1 Mini
32.4
Fiction.LiveBench
GPT-4.1 Mini leads by +11.1
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
Gemma 3 27B (free)
33.3
GPT-4.1 Mini
44.4
GPQA diamond
GPT-4.1 Mini leads by +22.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemma 3 27B (free)
31.8
GPT-4.1 Mini
54.5
MATH level 5
GPT-4.1 Mini leads by +13.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemma 3 27B (free)
74.0
GPT-4.1 Mini
87.3
OTIS Mock AIME 2024-2025
GPT-4.1 Mini leads by +25.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemma 3 27B (free)
19.6
GPT-4.1 Mini
44.7
Full benchmark table
| Benchmark | Gemma 3 27B (free) | GPT-4.1 Mini |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 4.9 | 32.4 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 33.3 | 44.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 31.8 | 54.5 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 74.0 | 87.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 19.6 | 44.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.00 | $0.00 | 131K tokens (~66 books) | — | |
| $0.40 | $1.60 | 1.0M tokens (~524 books) | $7.00 |
People also compared