Model comparison
Gemma 1.1 2b IT vs Mixtral 8x7B
Gemma 1.1 2b IT is the stronger model overall, scoring 28.8 to 26.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
Mistral AISummary
- They share 16 benchmarks with published results for both. Gemma 1.1 2b IT scores higher in 3 categories and Mixtral 8x7B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 1.1 2b IT leads 26.0 to 11.0.
Side by side
| Gemma 1.1 2b IT | Mixtral 8x7B | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 28.8 | 26.8 |
| Released | — | 2023-12-11 |
| Weights | Open | Open |
| Context window | — | 32K |
| Max output | — | 32K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 16 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Gemma 1.1 2b IT: 29.6 (#294), Mixtral 8x7B: 32.2 (#265)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1034 | 1127 |
| HumanEval+ | 17.7% | 39.6% |
| MBPP+ | 23.3% | 49.7% |
Reasoning Too close to call
Gemma 1.1 2b IT: 18.2 (#268), Mixtral 8x7B: 17.4 (#283)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1005 | 1115 |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| Epoch Capabilities Index | — | 118.38 |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 28.3 (#230), Mixtral 8x7B: 17.2 (#284)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1047 | 1147 |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Gemma 1.1 2b IT leads
Gemma 1.1 2b IT: 26.0 (#255), Mixtral 8x7B: 11.0 (#296)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Expert | 970 | 1088 |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual Mixtral 8x7B leads
Gemma 1.1 2b IT: 24.7 (#284), Mixtral 8x7B: 29.8 (#261)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 988 | 1077 |
| LMArena Chinese | 1011 | 1055 |
| LMArena German | 944 | 1114 |
| LMArena Korean | 899 | 968 |
| LMArena Russian | 990 | 1090 |
| LMArena French | — | 1165 |
| LMArena Japanese | — | 931 |
| LMArena Spanish | — | 1110 |
Instruction Following Mixtral 8x7B leads
Gemma 1.1 2b IT: 50.1 (#294), Mixtral 8x7B: 51.2 (#292)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 992 | 1110 |
| IFEval | — | 57.5% |
Long Context Mixtral 8x7B leads
Gemma 1.1 2b IT: 30.5 (#281), Mixtral 8x7B: 33.4 (#255)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1003 | 1103 |
Writing & Preference Mixtral 8x7B leads
Gemma 1.1 2b IT: 25.3 (#301), Mixtral 8x7B: 34.4 (#265)
| Benchmark | Gemma 1.1 2b IT | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1022 | 1132 |
| LMArena Creative Writing | 998 | 1109 |
| LMArena Multi-Turn | 958 | 1115 |
| WildBench | — | 67.3% |
Frequently asked questions
Is Gemma 1.1 2b IT better than Mixtral 8x7B?
Gemma 1.1 2b IT is the stronger model overall, scoring 28.8 to 26.8 on the Noometry Index.
Is Gemma 1.1 2b IT or Mixtral 8x7B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.2 versus 29.6 in the Noometry coding category.
How many benchmarks do Gemma 1.1 2b IT and Mixtral 8x7B share?
16 benchmarks have published results for both models. Gemma 1.1 2b IT has 16 scored results on Noometry and Mixtral 8x7B has 38.