Model comparison
Gemma 3 27B vs Ministral 8B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 28.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
Mistral AISummary
- They share 17 benchmarks with published results for both. Gemma 3 27B scores higher in 6 categories and Ministral 8B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 39.6.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 14.9% for Ministral 8B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.15 / $0.15 for Ministral 8B.
- Ministral 8B accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 27B | Ministral 8B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.8 | 28.2 |
| Released | 2025-03-11 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 262K |
| Input $ / M tokens | $0.08 | $0.15 |
| Output $ / M tokens | $0.16 | $0.15 |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Gemma 3 27B: 22.5 (#334), Ministral 8B: 35.0 (#230)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1322 | 1202 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Gemma 3 27B leads
Gemma 3 27B: 25.1 (#110), Ministral 8B: 16.4 (#148)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 11.1% |
Reasoning Ministral 8B leads
Gemma 3 27B: 16.7 (#301), Ministral 8B: 18.4 (#281)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1191 |
| DTBench | 52.5% | 45.7% |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Too close to call
Gemma 3 27B: 25.9 (#265), Ministral 8B: 25.7 (#267)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Math | 1312 | 1188 |
| MATH Level 5 | 74% | 14.9% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), Ministral 8B: 12.6 (#297)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 47.7% | 27.1% |
| Vectara Hallucination Rate | 7.4% | 7.4% |
| LMArena Expert | 1304 | 1170 |
| Confabulations | 40.3% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Ministral 8B: —
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Ministral 8B: 35.1 (#247)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1334 | 1165 |
| LMArena Chinese | 1346 | 1193 |
| LMArena Russian | 1349 | 1195 |
| LMArena French | 1368 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Ministral 8B: 60.5 (#250)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1161 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Ministral 8B leads
Gemma 3 27B: 27.6 (#293), Ministral 8B: 36.7 (#227)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1333 | 1212 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Ministral 8B: 39.6 (#246)
| Benchmark | Gemma 3 27B | Ministral 8B |
|---|---|---|
| LMArena Text | 1358 | 1191 |
| LMArena Creative Writing | 1346 | 1175 |
| LMArena Multi-Turn | 1345 | 1166 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Ministral 8B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 28.2 on the Noometry Index.
Which is cheaper, Gemma 3 27B or Ministral 8B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Ministral 8B lists at $0.15 and $0.15.
Is Gemma 3 27B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 27B and Ministral 8B share?
17 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Ministral 8B has 17.