Model comparison
Mistral 7B vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Mistral 7B costs 12× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Mistral Large in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 50.3% for Mistral Large.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 8K.
Side by side
| Mistral 7B | Mistral Large | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 23.0 | 31.9 |
| Released | 2023-09-27 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 8K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $0.25 | $2 |
| Output $ / M tokens | $0.25 | $6 |
| Results tracked | 37 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral 7B: 26.4 (#326), Mistral Large: 34.3 (#240)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 30% |
| LMArena Coding | 1082 | 1277 |
| BigCodeBench Complete | 27.3% | 38.3% |
| HumanEval+ | 36% | 62.2% |
| MBPP+ | 42.1% | 59.5% |
| SciCode | — | 36.2% |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Not comparable
Mistral 7B: —, Mistral Large: 28.6 (#89)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Mistral Large leads
Mistral 7B: 13.1 (#336), Mistral Large: 15.8 (#310)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1257 |
| DTBench | 42.5% | 65.1% |
| Epoch Capabilities Index | 112.21 | 128.52 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| ForecastBench | — | 57.1 |
| HellaSwag | 81% | — |
| LiveBench | — | 48.4% |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Mistral Large leads
Mistral 7B: 8.1 (#325), Mistral Large: 18.2 (#291)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 8.5% |
| LMArena Math | 1085 | 1262 |
| MATH Level 5 | 3.7% | 50.3% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 54.4% | — |
Knowledge Mistral Large leads
Mistral 7B: 7.4 (#311), Mistral Large: 30.1 (#230)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| GPQA Diamond | 15.2% | 51.3% |
| LMArena Expert | 1036 | 1232 |
| MMLU | 62.5% | 80% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multilingual Mistral Large leads
Mistral 7B: 25.8 (#283), Mistral Large: 40.0 (#219)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1012 | 1237 |
| LMArena Chinese | 1009 | 1240 |
| LMArena French | 1037 | 1325 |
| LMArena German | 987 | 1254 |
| LMArena Japanese | 878 | 1188 |
| LMArena Russian | 1018 | 1257 |
| LMArena Spanish | 1026 | 1268 |
| LMArena Korean | — | 1202 |
Instruction Following Mistral Large leads
Mistral 7B: 54.2 (#280), Mistral Large: 67.9 (#191)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1060 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Mistral 7B: 32.2 (#271), Mistral Large: 38.3 (#199)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1060 | 1261 |
Writing & Preference Mistral Large leads
Mistral 7B: 30.7 (#286), Mistral Large: 40.7 (#242)
| Benchmark | Mistral 7B | Mistral Large |
|---|---|---|
| LMArena Text | 1090 | 1266 |
| LMArena Creative Writing | 1068 | 1243 |
| LMArena Multi-Turn | 1062 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Mistral 7B better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 23.0 on the Noometry Index. Mistral 7B costs 12× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Mistral Large?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral 7B or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 8K.
How many benchmarks do Mistral 7B and Mistral Large share?
26 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Large has 51.