Model comparison
Mistral 7B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 23.0 on the Noometry Index.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 46.8% for Mistral Small.
- Both cost about the same: $0.25 input and $0.25 output per million tokens.
- Mistral Small accepts more context: 262K tokens versus 8K.
Side by side
| Mistral 7B | Mistral Small | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 23.0 | 33.4 |
| Released | 2023-09-27 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 8K | 256K |
| Input $ / M tokens | $0.25 | $0.15 |
| Output $ / M tokens | $0.25 | $0.60 |
| Results tracked | 37 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Mistral 7B: 26.4 (#326), Mistral Small: 34.0 (#247)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 36.1% |
| LMArena Coding | 1082 | 1362 |
| BigCodeBench Complete | 27.3% | 46.6% |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |
Agentic & Tool Use Not comparable
Mistral 7B: —, Mistral Small: 28.1 (#93)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
Reasoning Mistral Small leads
Mistral 7B: 13.1 (#336), Mistral Small: 19.8 (#250)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1335 |
| DTBench | 42.5% | 70.9% |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| LiveBench | — | 44% |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |
Math Mistral Small leads
Mistral 7B: 8.1 (#325), Mistral Small: 16.4 (#293)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 5.8% |
| LMArena Math | 1085 | 1341 |
| MATH Level 5 | 3.7% | 46.8% |
| LiveBench Math | — | 39.9% |
| GSM8K | 54.4% | — |
Knowledge Mistral Small leads
Mistral 7B: 7.4 (#311), Mistral Small: 31.0 (#222)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| GPQA Diamond | 15.2% | 47.5% |
| LMArena Expert | 1036 | 1291 |
| MMLU | 62.5% | 68.7% |
| Vectara Hallucination Rate | — | 5.1% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |
Multimodal Not comparable
Mistral 7B: —, Mistral Small: 33.5 (#96)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Mistral 7B: 25.8 (#283), Mistral Small: 45.5 (#169)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1012 | 1315 |
| LMArena Chinese | 1009 | 1340 |
| LMArena French | 1037 | 1337 |
| LMArena German | 987 | 1340 |
| LMArena Japanese | 878 | 1275 |
| LMArena Russian | 1018 | 1324 |
| LMArena Spanish | 1026 | 1346 |
| LMArena Korean | — | 1259 |
Instruction Following Mistral Small leads
Mistral 7B: 54.2 (#280), Mistral Small: 66.4 (#209)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1060 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context Mistral Small leads
Mistral 7B: 32.2 (#271), Mistral Small: 40.4 (#156)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1060 | 1327 |
Writing & Preference Mistral Small leads
Mistral 7B: 30.7 (#286), Mistral Small: 52.5 (#171)
| Benchmark | Mistral 7B | Mistral Small |
|---|---|---|
| LMArena Text | 1090 | 1338 |
| LMArena Creative Writing | 1068 | 1305 |
| LMArena Multi-Turn | 1062 | 1344 |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Mistral 7B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 23.0 on the Noometry Index.
Which is cheaper, Mistral 7B or Mistral Small?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is Mistral 7B or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Small does, with 262K tokens against 8K.
How many benchmarks do Mistral 7B and Mistral Small share?
23 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Small has 39.