Model comparison
Claude 3 Sonnet vs Ministral 8B
Claude 3 Sonnet and Ministral 8B score almost the same on the Noometry Index (29.0 vs 28.2), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Mistral AISummary
- They share 15 benchmarks with published results for both. Claude 3 Sonnet scores higher in 5 categories and Ministral 8B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 8B leads 25.7 to 10.7.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Claude 3 Sonnet and 27.1% for Ministral 8B.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Ministral 8B | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.0 | 28.2 |
| Released | 2024-02-29 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 30 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Claude 3 Sonnet: 29.6 (#302), Ministral 8B: 35.0 (#230)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Coding | 1223 | 1202 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, Ministral 8B: 16.4 (#148)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), Ministral 8B: 18.4 (#281)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1191 |
| DTBench | 53.6% | 45.7% |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Ministral 8B leads
Claude 3 Sonnet: 10.7 (#310), Ministral 8B: 25.7 (#267)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Math | 1213 | 1188 |
| MATH Level 5 | 18.2% | 14.9% |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
Knowledge Claude 3 Sonnet leads
Claude 3 Sonnet: 21.1 (#276), Ministral 8B: 12.6 (#297)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| GPQA Diamond | 40.6% | 27.1% |
| LMArena Expert | 1173 | 1170 |
| Vectara Hallucination Rate | — | 7.4% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), Ministral 8B: —
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 37.8 (#234), Ministral 8B: 35.1 (#247)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1205 | 1165 |
| LMArena Chinese | 1189 | 1193 |
| LMArena Russian | 1227 | 1195 |
| LMArena French | 1229 | — |
| LMArena German | 1204 | — |
| LMArena Japanese | 1131 | — |
| LMArena Korean | 1128 | — |
| LMArena Spanish | 1204 | — |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 62.8 (#235), Ministral 8B: 60.5 (#250)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1199 | 1161 |
Long Context Too close to call
Claude 3 Sonnet: 36.7 (#228), Ministral 8B: 36.7 (#227)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1211 | 1212 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.1 (#238), Ministral 8B: 39.6 (#246)
| Benchmark | Claude 3 Sonnet | Ministral 8B |
|---|---|---|
| LMArena Text | 1218 | 1191 |
| LMArena Creative Writing | 1186 | 1175 |
| LMArena Multi-Turn | 1227 | 1166 |
Frequently asked questions
Is Claude 3 Sonnet better than Ministral 8B?
Claude 3 Sonnet and Ministral 8B score almost the same on the Noometry Index (29.0 vs 28.2), so choose on price, context window or the category you care about most.
Is Claude 3 Sonnet or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Ministral 8B share?
15 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Ministral 8B has 17.