Model comparison
Gemma 2 27B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 29.4 on the Noometry Index.
Last verified . 32 shared benchmarks.
Google
Mistral AISummary
- They share 32 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and Mistral Small in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 19.0.
- The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 70.9% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Mistral Small accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 2 27B | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 29.4 | 33.4 |
| Released | 2024-06-24 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 2K | 256K |
| Input $ / M tokens | $0.65 | $0.15 |
| Output $ / M tokens | $0.65 | $0.60 |
| Results tracked | 34 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 27B: 34.1 (#246), Mistral Small: 34.0 (#247)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 36.1% |
| LiveBench Coding | 36% | 36.2% |
| LMArena Coding | 1211 | 1362 |
| BigCodeBench Complete | 52.5% | 46.6% |
| SciCode | — | 26.5% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Mistral Small: 28.1 (#93)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Gemma 2 27B: 15.3 (#315), Mistral Small: 19.8 (#250)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 28.1% | 44.8% |
| LMArena Hard Prompts | 1198 | 1335 |
| DTBench | 48% | 70.9% |
| LiveBench Data Analysis | 47.9% | 53.7% |
| LMCA | 7.1% | 20.6% |
| LiveBench | 38.2% | 44% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Epoch Capabilities Index | 122.08 | — |
Math Mistral Small leads
Gemma 2 27B: 10.7 (#311), Mistral Small: 16.4 (#293)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 5.8% |
| LiveBench Math | 26.5% | 39.9% |
| LMArena Math | 1212 | 1341 |
| MATH Level 5 | 27.9% | 46.8% |
Knowledge Mistral Small leads
Gemma 2 27B: 19.0 (#280), Mistral Small: 31.0 (#222)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| GPQA Diamond | 36.5% | 47.5% |
| LMArena Expert | 1172 | 1291 |
| MMLU | 75.7% | 68.7% |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multimodal Not comparable
Gemma 2 27B: —, Mistral Small: 33.5 (#96)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Gemma 2 27B: 38.6 (#226), Mistral Small: 45.5 (#169)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1217 | 1315 |
| LMArena Chinese | 1221 | 1340 |
| LMArena French | 1247 | 1337 |
| LMArena German | 1209 | 1340 |
| LMArena Japanese | 1175 | 1275 |
| LMArena Korean | 1174 | 1259 |
| LMArena Russian | 1234 | 1324 |
| LMArena Spanish | 1228 | 1346 |
Instruction Following Mistral Small leads
Gemma 2 27B: 60.5 (#249), Mistral Small: 66.4 (#209)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 63.7% |
| LMArena Instruction Following | 1206 | 1310 |
Long Context Mistral Small leads
Gemma 2 27B: 37.3 (#218), Mistral Small: 40.4 (#156)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1231 | 1327 |
Writing & Preference Mistral Small leads
Gemma 2 27B: 44.2 (#225), Mistral Small: 52.5 (#171)
| Benchmark | Gemma 2 27B | Mistral Small |
|---|---|---|
| LMArena Text | 1231 | 1338 |
| LMArena Creative Writing | 1241 | 1305 |
| LMArena Multi-Turn | 1224 | 1344 |
| LiveBench Language | 32.6% | 30.5% |
Frequently asked questions
Is Gemma 2 27B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Mistral Small better for coding?
They score almost the same on coding (34.1 vs 34.0); test both on your own repository before choosing.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 8K.
How many benchmarks do Gemma 2 27B and Mistral Small share?
32 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Mistral Small has 39.