Model comparison
Llama-3.3-70B-Instruct vs Ministral 8B
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 27.8 on the Noometry Index. Ministral 8B costs 1.6× less per token, which makes it the better buy when Llama-3.3-70B-Instruct's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 5 categories and Ministral 8B in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.5 to 12.5.
- The biggest single-benchmark swing is MATH Level 5: 41.6% for Llama-3.3-70B-Instruct and 14.9% for Ministral 8B.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.10 / $0.32 for Llama-3.3-70B-Instruct.
Side by side
| Llama-3.3-70B-Instruct | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.3 | 27.8 |
| Released | 2024-12-06 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.10 | $0.10 |
| Output $ / M tokens | $0.32 | $0.10 |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama-3.3-70B-Instruct: 30.6 (#284), Ministral 8B: 34.4 (#226)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Coding | 1268 | 1202 |
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 25.6 (#100), Ministral 8B: 16.2 (#140)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | 11.1% |
| BALROG | 23% | — |
Reasoning Ministral 8B leads
Llama-3.3-70B-Instruct: 13.7 (#325), Ministral 8B: 17.7 (#279)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1191 |
| DTBench | 59.5% | 45.7% |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| Epoch Capabilities Index | 127.32 | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
Math Ministral 8B leads
Llama-3.3-70B-Instruct: 14.3 (#292), Ministral 8B: 23.7 (#262)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Math | 1268 | 1188 |
| MATH Level 5 | 41.6% | 14.9% |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.5 (#220), Ministral 8B: 12.5 (#292)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| GPQA Diamond | 47.4% | 27.1% |
| Vectara Hallucination Rate | 4.1% | 7.4% |
| LMArena Expert | 1225 | 1170 |
| Confabulations | 22.8% | — |
| MMLU | 86.3% | — |
Multilingual Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 40.1 (#215), Ministral 8B: 35.3 (#242)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1236 | 1165 |
| LMArena Chinese | 1217 | 1193 |
| LMArena Russian | 1252 | 1195 |
| LMArena French | 1280 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1149 | — |
| LMArena Korean | 1142 | — |
| LMArena Spanish | 1269 | — |
Instruction Following Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 71.3 (#152), Ministral 8B: 60.7 (#245)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1242 | 1161 |
| LiveBench Instruction Following | 82.7% | — |
Long Context Ministral 8B leads
Llama-3.3-70B-Instruct: 26.4 (#290), Ministral 8B: 36.7 (#222)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1256 | 1212 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.8 (#203), Ministral 8B: 39.8 (#241)
| Benchmark | Llama-3.3-70B-Instruct | Ministral 8B |
|---|---|---|
| LMArena Text | 1274 | 1191 |
| LMArena Creative Writing | 1250 | 1175 |
| LMArena Multi-Turn | 1279 | 1166 |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Ministral 8B?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.3 to 27.8 on the Noometry Index. Ministral 8B costs 1.6× less per token, which makes it the better buy when Llama-3.3-70B-Instruct's lead doesn't matter for your workload.
Which is cheaper, Llama-3.3-70B-Instruct or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Llama-3.3-70B-Instruct lists at $0.10 and $0.32.
Is Llama-3.3-70B-Instruct or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 34.4 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama-3.3-70B-Instruct and Ministral 8B share?
17 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Ministral 8B has 17.