Model comparison
Gemma 3 27B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.1 to 30.5 on the Noometry Index. Gemma 3 27B costs 2.6× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Google
Mistral AISummary
- They share 35 benchmarks with published results for both. Gemma 3 27B scores higher in 4 categories and Mistral Small in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Small leads 40.4 to 27.6.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 46.8% for Mistral Small.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 256K tokens versus 131K.
Side by side
| Gemma 3 27B | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.5 | 33.1 |
| Released | 2025-03-11 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 8K | 256K |
| Input $ / M tokens | $0.08 | $0.15 |
| Output $ / M tokens | $0.16 | $0.60 |
| Results tracked | 43 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Gemma 3 27B: 22.1 (#329), Mistral Small: 33.5 (#242)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| SciCode | 21.2% | 26.5% |
| LiveBench Coding | 39.9% | 36.2% |
| LMArena Coding | 1322 | 1363 |
| Aider Polyglot | 4.9% | — |
| BigCodeBench Instruct | — | 36.1% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Mistral Small leads
Gemma 3 27B: 24.9 (#105), Mistral Small: 27.9 (#87)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 37.1% |
Reasoning Mistral Small leads
Gemma 3 27B: 16.3 (#297), Mistral Small: 19.3 (#238)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 37.8% |
| CritPt | 0% | 0% |
| LiveBench Reasoning | 43.8% | 44.8% |
| LMArena Hard Prompts | 1340 | 1336 |
| DTBench | 52.5% | 70.9% |
| LiveBench Data Analysis | 51.5% | 53.7% |
| LMCA | 12.3% | 20.6% |
| LiveBench | 50% | 44% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 130.04 | — |
Math Gemma 3 27B leads
Gemma 3 27B: 24.4 (#261), Mistral Small: 15.4 (#287)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 5.8% |
| LiveBench Math | 55.4% | 39.9% |
| LMArena Math | 1312 | 1341 |
| MATH Level 5 | 74% | 46.8% |
Knowledge Mistral Small leads
Gemma 3 27B: 25.4 (#256), Mistral Small: 30.9 (#214)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| GPQA Diamond | 47.7% | 47.5% |
| Vectara Hallucination Rate | 7.4% | 5.1% |
| LMArena Expert | 1303 | 1293 |
| Confabulations | 40.3% | — |
| MMLU | — | 68.7% |
Multimodal Too close to call
Gemma 3 27B: 32.0 (#94), Mistral Small: 32.9 (#91)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| LMArena Vision | 1165 | 1142 |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 47.0 (#150), Mistral Small: 45.7 (#164)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1334 | 1315 |
| LMArena Chinese | 1347 | 1342 |
| LMArena French | 1368 | 1337 |
| LMArena German | 1362 | 1341 |
| LMArena Japanese | 1287 | 1275 |
| LMArena Korean | 1308 | 1260 |
| LMArena Russian | 1349 | 1324 |
| LMArena Spanish | 1348 | 1346 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.8 (#155), Mistral Small: 66.6 (#204)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 74.9% | 63.7% |
| LMArena Instruction Following | 1321 | 1310 |
Long Context Mistral Small leads
Gemma 3 27B: 27.6 (#288), Mistral Small: 40.4 (#151)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1333 | 1327 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Too close to call
Gemma 3 27B: 52.7 (#161), Mistral Small: 52.6 (#165)
| Benchmark | Gemma 3 27B | Mistral Small |
|---|---|---|
| LMArena Text | 1358 | 1338 |
| LMArena Creative Writing | 1346 | 1304 |
| LMArena Multi-Turn | 1344 | 1344 |
| LiveBench Language | 34.6% | 30.5% |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
Frequently asked questions
Is Gemma 3 27B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.1 to 30.5 on the Noometry Index. Gemma 3 27B costs 2.6× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Mistral Small?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Gemma 3 27B or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 33.5 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 256K tokens against 131K.
How many benchmarks do Gemma 3 27B and Mistral Small share?
35 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Mistral Small has 39.