Model comparison
Claude 3 Haiku vs Phi 3 Mini 128k Instruct
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 25.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
MicrosoftSummary
- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Phi 3 Mini 128k Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 31.6 to 9.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 39.4% for Claude 3 Haiku and 29.6% 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 Haiku | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 25.9 | 29.7 |
| Released | 2024-03-07 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 128k Instruct leads
Claude 3 Haiku: 26.4 (#325), Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 29.6% |
| LMArena Coding | 1199 | 1039 |
| BigCodeBench Complete | 50.1% | 40.6% |
| WeirdML | 9.8% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Phi 3 Mini 128k Instruct leads
Claude 3 Haiku: 16.3 (#307), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1028 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Phi 3 Mini 128k Instruct leads
Claude 3 Haiku: 9.8 (#319), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1188 | 1089 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge Phi 3 Mini 128k Instruct leads
Claude 3 Haiku: 17.3 (#285), Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1148 | 984 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Phi 3 Mini 128k Instruct: —
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.0 (#243), Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1178 | 1000 |
| LMArena Chinese | 1155 | 1016 |
| LMArena French | 1195 | 1039 |
| LMArena German | 1174 | 1006 |
| LMArena Japanese | 1102 | 899 |
| LMArena Korean | 1109 | 856 |
| LMArena Russian | 1204 | 1004 |
| LMArena Spanish | 1166 | 1059 |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.3 (#247), Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1173 | 1023 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#237), Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1190 | 996 |
Writing & Preference Claude 3 Haiku leads
Claude 3 Haiku: 29.7 (#291), Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | Claude 3 Haiku | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1195 | 1050 |
| LMArena Creative Writing | 1157 | 1024 |
| LMArena Multi-Turn | 1190 | 989 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Phi 3 Mini 128k Instruct?
Phi 3 Mini 128k Instruct is the stronger model overall, scoring 29.7 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Phi 3 Mini 128k Instruct better for coding?
Phi 3 Mini 128k Instruct scores higher on coding benchmarks: 28.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Phi 3 Mini 128k Instruct share?
19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.