Model comparison
Gemma 3 27B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 3.8× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Google
Mistral AISummary
- They share 21 benchmarks with published results for both. Gemma 3 27B scores higher in 1 category and Mistral Large 3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Large 3 leads 43.1 to 27.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 40.4% for Gemma 3 27B and 50.9% for Mistral Large 3.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 27B | Mistral Large 3 | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.5 | 38.6 |
| Released | 2025-03-11 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.08 | $0.25 |
| Output $ / M tokens | $0.16 | $0.75 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Gemma 3 27B: 22.1 (#329), Mistral Large 3: 34.1 (#230)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1322 | 1447 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1230 |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Not comparable
Gemma 3 27B: 24.9 (#105), Mistral Large 3: —
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Gemma 3 27B leads
Gemma 3 27B: 16.3 (#297), Mistral Large 3: 14.6 (#314)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 40.4% | 50.9% |
| LMArena Hard Prompts | 1340 | 1429 |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 23% |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Mistral Large 3 leads
Gemma 3 27B: 24.4 (#261), Mistral Large 3: 36.0 (#131)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1312 | 1415 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Mistral Large 3 leads
Gemma 3 27B: 25.4 (#256), Mistral Large 3: 35.5 (#173)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 14.5% |
| LMArena Expert | 1303 | 1421 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
Multimodal Mistral Large 3 leads
Gemma 3 27B: 32.0 (#94), Mistral Large 3: 37.6 (#65)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1165 | 1222 |
| GeoBench | 52% | — |
Multilingual Mistral Large 3 leads
Gemma 3 27B: 47.0 (#150), Mistral Large 3: 52.6 (#79)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1334 | 1412 |
| LMArena Chinese | 1347 | 1448 |
| LMArena French | 1368 | 1456 |
| LMArena German | 1362 | 1438 |
| LMArena Japanese | 1287 | 1399 |
| LMArena Korean | 1308 | 1384 |
| LMArena Russian | 1349 | 1412 |
| LMArena Spanish | 1348 | 1437 |
Instruction Following Mistral Large 3 leads
Gemma 3 27B: 70.8 (#155), Mistral Large 3: 74.1 (#104)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1402 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Mistral Large 3 leads
Gemma 3 27B: 27.6 (#288), Mistral Large 3: 43.1 (#102)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1333 | 1413 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Mistral Large 3 leads
Gemma 3 27B: 52.7 (#161), Mistral Large 3: 60.2 (#100)
| Benchmark | Gemma 3 27B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1358 | 1427 |
| LMArena Creative Writing | 1346 | 1385 |
| EQ-Bench Creative Writing | 1266 | 1412 |
| LMArena Multi-Turn | 1344 | 1429 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.5 on the Noometry Index. Gemma 3 27B costs 3.8× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Mistral Large 3?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Gemma 3 27B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 27B and Mistral Large 3 share?
21 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Mistral Large 3 has 24.