Model comparison
Claude 3 Sonnet vs Phi 3 Mini 128k Instruct
Claude 3 Sonnet and Phi 3 Mini 128k Instruct score almost the same on the Noometry Index (28.8 vs 29.1), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
MicrosoftSummary
- They share 19 benchmarks with published results for both. Claude 3 Sonnet scores higher in 6 categories and Phi 3 Mini 128k Instruct in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 29.2 to 10.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet and 40.6% for Phi 3 Mini 128k Instruct.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Sonnet | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 28.8 | 29.1 |
| Released | 2024-02-29 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3 Sonnet: 29.2 (#296), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 42.7% | 29.6% |
| LMArena Coding | 1223 | 1040 |
| BigCodeBench Complete | 53.8% | 40.6% |
| WeirdML | 10.2% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Too close to call
Claude 3 Sonnet: 19.7 (#232), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1028 |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.69 | — |
| WinoGrande | 75.1% | — |
Math Phi 3 Mini 128k Instruct leads
Claude 3 Sonnet: 10.0 (#305), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1213 | 1089 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge Phi 3 Mini 128k Instruct leads
Claude 3 Sonnet: 21.1 (#271), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1173 | 984 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Phi 3 Mini 128k Instruct: —
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Claude 3 Sonnet leads
Claude 3 Sonnet: 38.0 (#229), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1205 | 1000 |
| LMArena Chinese | 1188 | 1016 |
| LMArena French | 1228 | 1038 |
| LMArena German | 1204 | 1006 |
| LMArena Japanese | 1131 | 899 |
| LMArena Korean | 1128 | 856 |
| LMArena Russian | 1227 | 1004 |
| LMArena Spanish | 1204 | 1058 |
Instruction Following Claude 3 Sonnet leads
Claude 3 Sonnet: 63.1 (#230), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1200 | 1023 |
Long Context Claude 3 Sonnet leads
Claude 3 Sonnet: 36.7 (#223), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1211 | 996 |
Writing & Preference Claude 3 Sonnet leads
Claude 3 Sonnet: 42.3 (#233), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | Claude 3 Sonnet | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1218 | 1050 |
| LMArena Creative Writing | 1186 | 1024 |
| LMArena Multi-Turn | 1227 | 989 |
Frequently asked questions
Is Claude 3 Sonnet better than Phi 3 Mini 128k Instruct?
Claude 3 Sonnet and Phi 3 Mini 128k Instruct score almost the same on the Noometry Index (28.8 vs 29.1), so choose on price, context window or the category you care about most.
Is Claude 3 Sonnet or Phi 3 Mini 128k Instruct better for coding?
They score almost the same on coding (29.2 vs 28.3); test both on your own repository before choosing.
How many benchmarks do Claude 3 Sonnet and Phi 3 Mini 128k Instruct share?
19 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.