Model comparison
Mistral vs Mistral 7B
Mistral is the stronger model overall, scoring 29.9 to 23.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Mistral scores higher in 7 categories and Mistral 7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral leads 22.3 to 8.1.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Mistral 7B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.9 | 23.0 |
| Released | — | 2023-09-27 |
| Weights | Proprietary | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 22 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.8 (#250), Mistral 7B: 26.4 (#326)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Coding | 1162 | 1082 |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Mistral leads
Mistral: 22.2 (#200), Mistral 7B: 13.1 (#336)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1067 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Mistral leads
Mistral: 22.3 (#278), Mistral 7B: 8.1 (#325)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Math | 1180 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Mistral leads
Mistral: 16.6 (#288), Mistral 7B: 7.4 (#311)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Expert | 1125 | 1036 |
| GPQA Diamond | — | 15.2% |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Mistral leads
Mistral: 32.8 (#254), Mistral 7B: 25.8 (#283)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1129 | 1012 |
| LMArena Chinese | 1109 | 1009 |
| LMArena French | 1180 | 1037 |
| LMArena German | 1155 | 987 |
| LMArena Japanese | 1013 | 878 |
| LMArena Russian | 1168 | 1018 |
| LMArena Spanish | 1143 | 1026 |
| LMArena Korean | 1032 | — |
Instruction Following Mistral 7B leads
Mistral: 52.6 (#288), Mistral 7B: 54.2 (#280)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1060 |
| IFEval | 56.8% | — |
Long Context Mistral leads
Mistral: 35.0 (#245), Mistral 7B: 32.2 (#271)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1153 | 1060 |
Writing & Preference Mistral leads
Mistral: 37.0 (#260), Mistral 7B: 30.7 (#286)
| Benchmark | Mistral | Mistral 7B |
|---|---|---|
| LMArena Text | 1165 | 1090 |
| LMArena Creative Writing | 1158 | 1068 |
| LMArena Multi-Turn | 1147 | 1062 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Mistral 7B?
Mistral is the stronger model overall, scoring 29.9 to 23.0 on the Noometry Index.
Is Mistral or Mistral 7B better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Mistral and Mistral 7B share?
16 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral 7B has 37.