Model comparison
Gemini 1.0 Pro vs Mistral
Mistral is the stronger model overall, scoring 29.9 to 27.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
Mistral AISummary
- They share 16 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 2 categories and Mistral in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral leads 22.3 to 9.3.
Side by side
| Gemini 1.0 Pro | Mistral | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 27.3 | 29.9 |
| Released | 2023-12-13 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Gemini 1.0 Pro: 32.2 (#275), Mistral: 33.8 (#250)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Coding | 1108 | 1162 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Mistral leads
Gemini 1.0 Pro: 17.1 (#296), Mistral: 22.2 (#200)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1149 |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 117.04 | — |
Math Mistral leads
Gemini 1.0 Pro: 9.3 (#321), Mistral: 22.3 (#278)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Math | 1132 | 1180 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 11.2% | — |
Knowledge Mistral leads
Gemini 1.0 Pro: 15.6 (#291), Mistral: 16.6 (#288)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Expert | 1059 | 1125 |
| GPQA Diamond | 34% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| MMLU | 70% | — |
Multilingual Too close to call
Gemini 1.0 Pro: 33.4 (#252), Mistral: 32.8 (#254)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Non-English | 1138 | 1129 |
| LMArena Chinese | 1124 | 1109 |
| LMArena French | 1145 | 1180 |
| LMArena German | 1125 | 1155 |
| LMArena Japanese | 1023 | 1013 |
| LMArena Russian | 1186 | 1168 |
| LMArena Spanish | 1119 | 1143 |
| LMArena Korean | — | 1032 |
Instruction Following Gemini 1.0 Pro leads
Gemini 1.0 Pro: 57.6 (#267), Mistral: 52.6 (#288)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Instruction Following | 1114 | 1152 |
| IFEval | — | 56.8% |
Long Context Too close to call
Gemini 1.0 Pro: 34.3 (#249), Mistral: 35.0 (#245)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Longer Query | 1132 | 1153 |
Writing & Preference Too close to call
Gemini 1.0 Pro: 36.0 (#264), Mistral: 37.0 (#260)
| Benchmark | Gemini 1.0 Pro | Mistral |
|---|---|---|
| LMArena Text | 1149 | 1165 |
| LMArena Creative Writing | 1131 | 1158 |
| LMArena Multi-Turn | 1139 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Gemini 1.0 Pro better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Mistral share?
16 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Mistral has 22.