Model comparison
Llama 3.1-8B vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.
Last verified . 23 shared benchmarks.
Meta
Mistral AISummary
- They share 23 benchmarks with published results for both. Llama 3.1-8B scores higher in 0 categories and Mistral Small 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 8.0.
- The biggest single-benchmark swing is GPQA Diamond: 27% for Llama 3.1-8B and 47.3% for Mistral Small 3.
- Both cost about the same: $0.05 input and $0.08 output per million tokens.
- Llama 3.1-8B accepts more context: 128K tokens versus 33K.
Side by side
| Llama 3.1-8B | Mistral Small 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 23.0 | 31.2 |
| Released | 2024-07-23 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 128K | 33K |
| Max output | 4K | 16K |
| Input $ / M tokens | $0.05 | $0.05 |
| Output $ / M tokens | $0.08 | $0.08 |
| Results tracked | 43 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Llama 3.1-8B: 20.2 (#340), Mistral Small 3: 36.5 (#207)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 32.8% | 45.3% |
| LMArena Coding | 1195 | 1246 |
| BigCodeBench Complete | 40.5% | 50.4% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| HumanEval+ | 62.8% | — |
| MBPP+ | 55.6% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Mistral Small 3: —
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Mistral Small 3 leads
Llama 3.1-8B: 14.9 (#321), Mistral Small 3: 18.9 (#273)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1175 | 1233 |
| Epoch Capabilities Index | 116.57 | 127.07 |
| CritPt | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| PIQA | 81.2% | — |
Math Mistral Small 3 leads
Llama 3.1-8B: 10.2 (#317), Mistral Small 3: 16.3 (#295)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | 6.7% |
| LMArena Math | 1179 | 1240 |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Mistral Small 3 leads
Llama 3.1-8B: 8.0 (#307), Mistral Small 3: 25.1 (#263)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 27% | 47.3% |
| LMArena Expert | 1144 | 1202 |
| MMLU-Pro | 40.6% | — |
| Confabulations | — | 25.2% |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Mistral Small 3 leads
Llama 3.1-8B: 34.0 (#249), Mistral Small 3: 37.3 (#236)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1148 | 1198 |
| LMArena Chinese | 1151 | 1204 |
| LMArena French | 1177 | 1203 |
| LMArena German | 1144 | 1211 |
| LMArena Japanese | 1061 | 1111 |
| LMArena Korean | 1053 | 1188 |
| LMArena Russian | 1158 | 1216 |
| LMArena Spanish | 1169 | — |
Instruction Following Mistral Small 3 leads
Llama 3.1-8B: 58.9 (#258), Mistral Small 3: 63.7 (#229)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1159 | 1214 |
| IFEval | 74.3% | — |
Long Context Mistral Small 3 leads
Llama 3.1-8B: 35.8 (#238), Mistral Small 3: 37.8 (#211)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1182 | 1246 |
Writing & Preference Mistral Small 3 leads
Llama 3.1-8B: 29.7 (#290), Mistral Small 3: 32.2 (#280)
| Benchmark | Llama 3.1-8B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1187 | 1234 |
| LMArena Creative Writing | 1154 | 1195 |
| EQ-Bench Creative Writing | 713 | 707 |
| LMArena Multi-Turn | 1172 | 1217 |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.
Which is cheaper, Llama 3.1-8B or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Llama 3.1-8B lists at $0.05 and $0.08.
Is Llama 3.1-8B or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 3.1-8B does, with 128K tokens against 33K.
How many benchmarks do Llama 3.1-8B and Mistral Small 3 share?
23 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Mistral Small 3 has 24.