Model comparison
Mistral 7B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Mistral 7B costs 1.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Mistral Large 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 8.1.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 8K.
Side by side
| Mistral 7B | Mistral Large 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 23.0 | 39.1 |
| Released | 2023-09-27 | 2025-12-02 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.25 | $0.25 |
| Output $ / M tokens | $0.25 | $0.75 |
| Results tracked | 37 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Mistral 7B: 26.4 (#326), Mistral Large 3: 34.4 (#237)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1082 | 1448 |
| LMArena WebDev | — | 1230 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Reasoning Mistral Large 3 leads
Mistral 7B: 13.1 (#336), Mistral Large 3: 15.2 (#319)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 23% |
| 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 Large 3 leads
Mistral 7B: 8.1 (#325), Mistral Large 3: 38.7 (#129)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1085 | 1414 |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |
Knowledge Mistral Large 3 leads
Mistral 7B: 7.4 (#311), Mistral Large 3: 36.0 (#177)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1036 | 1421 |
| GPQA Diamond | 15.2% | — |
| Vectara Hallucination Rate | — | 14.5% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multimodal Not comparable
Mistral 7B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Mistral 7B: 25.8 (#283), Mistral Large 3: 52.5 (#84)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1012 | 1413 |
| LMArena Chinese | 1009 | 1447 |
| LMArena French | 1037 | 1455 |
| LMArena German | 987 | 1437 |
| LMArena Japanese | 878 | 1394 |
| LMArena Russian | 1018 | 1411 |
| LMArena Spanish | 1026 | 1440 |
| LMArena Korean | — | 1384 |
Instruction Following Mistral Large 3 leads
Mistral 7B: 54.2 (#280), Mistral Large 3: 74.0 (#108)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1060 | 1403 |
Long Context Mistral Large 3 leads
Mistral 7B: 32.2 (#271), Mistral Large 3: 43.1 (#105)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1060 | 1413 |
Writing & Preference Mistral Large 3 leads
Mistral 7B: 30.7 (#286), Mistral Large 3: 60.0 (#101)
| Benchmark | Mistral 7B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1090 | 1428 |
| LMArena Creative Writing | 1068 | 1386 |
| LMArena Multi-Turn | 1062 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is Mistral 7B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 23.0 on the Noometry Index. Mistral 7B costs 1.5× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.
Which is cheaper, Mistral 7B or Mistral Large 3?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Mistral 7B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 8K.
How many benchmarks do Mistral 7B and Mistral Large 3 share?
16 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Large 3 has 24.