Model comparison
Claude 3 Haiku vs phi-3-medium 14B
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 25.9 on the Noometry Index.
Last verified . 7 shared benchmarks.
MicrosoftSummary
- They share 7 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 27.3 to 9.8.
- The biggest single-benchmark swing is GPQA Diamond: 36.3% for Claude 3 Haiku and 27.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | phi-3-medium 14B | |
|---|---|---|
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
Claude 3 Haiku: 26.4 (#325), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 37.6% |
| BigCodeBench Complete | 50.1% | 48.7% |
| WeirdML | 9.8% | — |
| LMArena Coding | 1199 | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning Not comparable
Claude 3 Haiku: 16.3 (#307), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 118.35 | 121.23 |
| WinoGrande | 74.2% | 81.5% |
| Kagi LLM Benchmark | 34.2% | — |
| LMArena Hard Prompts | 1174 | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 82.4% |
Math phi-3-medium 14B leads
Claude 3 Haiku: 9.8 (#319), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 14.9% | 17.6% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LMArena Math | 1188 | — |
Knowledge Claude 3 Haiku leads
Claude 3 Haiku: 17.3 (#285), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 36.3% | 27.6% |
| MMLU | 73.8% | 78% |
| Confabulations | 34.2% | — |
| LMArena Expert | 1148 | — |
| ARC (AI2) Challenge | — | 91.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Not comparable
Claude 3 Haiku: 36.0 (#243), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1178 | — |
| LMArena Chinese | 1155 | — |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Russian | 1204 | — |
| LMArena Spanish | 1166 | — |
Instruction Following Not comparable
Claude 3 Haiku: 61.3 (#247), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1173 | — |
Long Context Not comparable
Claude 3 Haiku: 36.1 (#237), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1190 | — |
Writing & Preference Not comparable
Claude 3 Haiku: 29.7 (#291), phi-3-medium 14B: —
| Benchmark | Claude 3 Haiku | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1195 | — |
| LMArena Creative Writing | 1157 | — |
| EQ-Bench Creative Writing | 717 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is Claude 3 Haiku better than phi-3-medium 14B?
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and phi-3-medium 14B share?
7 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and phi-3-medium 14B has 13.