Model comparison
Claude 3 Sonnet vs Ministral 3B
Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 25.6 on the Noometry Index.
Last verified . 4 shared benchmarks.
Mistral AISummary
- They share 4 benchmarks with published results for both. Claude 3 Sonnet scores higher in 2 categories and Ministral 3B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 24.5 to 10.0.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 25.3% for Ministral 3B.
- Ministral 3B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Ministral 3B | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 28.8 | 25.6 |
| Released | 2024-02-29 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.04 |
| Results tracked | 30 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 3 Sonnet: 29.2 (#296), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| LMArena Coding | 1223 | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 19.7 (#232), Ministral 3B: 17.7 (#278)
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| DTBench | 53.6% | 51.7% |
| Epoch Capabilities Index | 120.69 | 118.08 |
| LMArena Hard Prompts | 1197 | — |
| LMCA | — | 5.5% |
| WinoGrande | 75.1% | — |
Math Ministral 3B leads
Claude 3 Sonnet: 10.0 (#305), Ministral 3B: 24.5 (#257)
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| MATH Level 5 | 18.2% | 14.4% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | 1213 | — |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#271), Ministral 3B: 10.4 (#297)
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| GPQA Diamond | 40.6% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1173 | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Not comparable
Claude 3 Sonnet: 38.0 (#229), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1188 | — |
| LMArena French | 1228 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Not comparable
Claude 3 Sonnet: 63.1 (#230), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1200 | — |
Long Context Not comparable
Claude 3 Sonnet: 36.7 (#223), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1211 | — |
Writing & Preference Not comparable
Claude 3 Sonnet: 42.3 (#233), Ministral 3B: —
| Benchmark | Claude 3 Sonnet | Ministral 3B |
|---|---|---|
| LMArena Text | 1218 | — |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1227 | — |
Frequently asked questions
Is Claude 3 Sonnet better than Ministral 3B?
Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 25.6 on the Noometry Index.
How many benchmarks do Claude 3 Sonnet and Ministral 3B share?
4 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Ministral 3B has 6.