Model comparison
Llama 3-8B vs Ministral 8B
Ministral 8B is the stronger model overall, scoring 27.8 to 25.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
Mistral AISummary
- They share 15 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Ministral 8B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 8B leads 23.7 to 8.3.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 14.9% for Ministral 8B.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.14 / $0.14 for Llama 3-8B.
- Ministral 8B accepts more context: 128K tokens versus 8K.
Side by side
| Llama 3-8B | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.3 | 27.8 |
| Released | 2024-04-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 8K | 128K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.14 | $0.10 |
| Output $ / M tokens | $0.14 | $0.10 |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama 3-8B: 30.5 (#285), Ministral 8B: 34.4 (#226)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1152 | 1202 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3-8B: —, Ministral 8B: 16.2 (#140)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Llama 3-8B: 13.8 (#321), Ministral 8B: 17.7 (#279)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1191 |
| DTBench | 43.9% | 45.7% |
| Chess Puzzles | 0% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Ministral 8B leads
Llama 3-8B: 8.3 (#317), Ministral 8B: 23.7 (#262)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Math | 1151 | 1188 |
| MATH Level 5 | 6.1% | 14.9% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
Knowledge Ministral 8B leads
Llama 3-8B: 7.8 (#303), Ministral 8B: 12.5 (#292)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 26.1% | 27.1% |
| LMArena Expert | 1113 | 1170 |
| Vectara Hallucination Rate | — | 7.4% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Ministral 8B leads
Llama 3-8B: 31.0 (#256), Ministral 8B: 35.3 (#242)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1098 | 1165 |
| LMArena Chinese | 1076 | 1193 |
| LMArena Russian | 1109 | 1195 |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Spanish | 1172 | — |
Instruction Following Ministral 8B leads
Llama 3-8B: 58.7 (#255), Ministral 8B: 60.7 (#245)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1127 | 1161 |
Long Context Ministral 8B leads
Llama 3-8B: 34.2 (#246), Ministral 8B: 36.7 (#222)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1128 | 1212 |
Writing & Preference Ministral 8B leads
Llama 3-8B: 37.7 (#251), Ministral 8B: 39.8 (#241)
| Benchmark | Llama 3-8B | Ministral 8B |
|---|---|---|
| LMArena Text | 1166 | 1191 |
| LMArena Creative Writing | 1150 | 1175 |
| LMArena Multi-Turn | 1152 | 1166 |
Frequently asked questions
Is Llama 3-8B better than Ministral 8B?
Ministral 8B is the stronger model overall, scoring 27.8 to 25.3 on the Noometry Index.
Which is cheaper, Llama 3-8B or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Llama 3-8B lists at $0.14 and $0.14.
Is Llama 3-8B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 34.4 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 128K tokens against 8K.
How many benchmarks do Llama 3-8B and Ministral 8B share?
15 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Ministral 8B has 17.