Model comparison
Gemma 3 27B vs Mixtral 8x7B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 27.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
Mistral AISummary
- They share 21 benchmarks with published results for both. Gemma 3 27B scores higher in 5 categories and Mixtral 8x7B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Gemma 3 27B leads 70.6 to 51.0.
- The biggest single-benchmark swing is MATH Level 5: 74% for Gemma 3 27B and 10% for Mixtral 8x7B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Gemma 3 27B accepts more context: 131K tokens versus 32K.
Side by side
| Gemma 3 27B | Mixtral 8x7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 30.8 | 27.1 |
| Released | 2025-03-11 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 131K | 32K |
| Max output | 8K | 32K |
| Input $ / M tokens | $0.08 | $0.70 |
| Output $ / M tokens | $0.16 | $0.70 |
| Results tracked | 43 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Gemma 3 27B: 22.5 (#334), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1322 | 1126 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Mixtral 8x7B: —
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Mixtral 8x7B leads
Gemma 3 27B: 16.7 (#301), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1115 |
| DTBench | 52.5% | 49.6% |
| Epoch Capabilities Index | 130.04 | 118.47 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| LiveBench | 50% | — |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Gemma 3 27B leads
Gemma 3 27B: 25.9 (#265), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1312 | 1147 |
| MATH Level 5 | 74% | 10% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| Omni-MATH | — | 10.5% |
| LiveBench Math | 55.4% | — |
| GSM8K | — | 74.4% |
Knowledge Gemma 3 27B leads
Gemma 3 27B: 25.5 (#261), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 47.7% | 30.6% |
| LMArena Expert | 1304 | 1088 |
| MMLU-Pro | — | 33.5% |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Mixtral 8x7B: —
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1334 | 1077 |
| LMArena Chinese | 1346 | 1055 |
| LMArena French | 1368 | 1166 |
| LMArena German | 1362 | 1114 |
| LMArena Japanese | 1287 | 931 |
| LMArena Korean | 1308 | 968 |
| LMArena Russian | 1349 | 1090 |
| LMArena Spanish | 1349 | 1111 |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1109 |
| LiveBench Instruction Following | 74.9% | — |
| IFEval | — | 57.5% |
Long Context Mixtral 8x7B leads
Gemma 3 27B: 27.6 (#293), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1333 | 1103 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Gemma 3 27B | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1358 | 1132 |
| LMArena Creative Writing | 1346 | 1109 |
| LMArena Multi-Turn | 1345 | 1115 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| WildBench | — | 67.3% |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Mixtral 8x7B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 27.1 on the Noometry Index.
Which is cheaper, Gemma 3 27B or Mixtral 8x7B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.
Is Gemma 3 27B or Mixtral 8x7B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Gemma 3 27B does, with 131K tokens against 32K.
How many benchmarks do Gemma 3 27B and Mixtral 8x7B share?
21 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Mixtral 8x7B has 38.