Model comparison
Claude 3.5 Haiku vs Phi 3 Small 8k Instruct
Claude 3.5 Haiku and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.2 vs 29.3), so choose on price, context window or the category you care about most.
Last verified . 25 shared benchmarks.
MicrosoftSummary
- They share 25 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Small 8k Instruct leads 27.6 to 14.7.
- The biggest single-benchmark swing is LiveBench Coding: 51.4% for Claude 3.5 Haiku and 20.3% for Phi 3 Small 8k Instruct.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 29.2 | 29.3 |
| Released | 2024-10-22 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 49 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Haiku leads
Claude 3.5 Haiku: 32.9 (#265), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 51.4% | 20.3% |
| LMArena Coding | 1286 | 1101 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Phi 3 Small 8k Instruct: —
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Claude 3.5 Haiku leads
Claude 3.5 Haiku: 17.7 (#290), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 28.1% | 15.9% |
| LMArena Hard Prompts | 1251 | 1100 |
| LiveBench Data Analysis | 48.5% | 30.3% |
| LiveBench | 43.5% | 24% |
| CritPt | 0% | — |
| DTBench | 56.7% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 127.15 | — |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math Phi 3 Small 8k Instruct leads
Claude 3.5 Haiku: 14.7 (#300), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 35.5% | 17.6% |
| LMArena Math | 1244 | 1151 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Phi 3 Small 8k Instruct leads
Claude 3.5 Haiku: 18.7 (#281), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1208 | 1067 |
| MMLU | 74.3% | 75.7% |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Phi 3 Small 8k Instruct: —
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Claude 3.5 Haiku leads
Claude 3.5 Haiku: 40.0 (#218), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1238 | 1058 |
| LMArena Chinese | 1229 | 1061 |
| LMArena French | 1264 | 1135 |
| LMArena German | 1237 | 1080 |
| LMArena Japanese | 1175 | 966 |
| LMArena Korean | 1173 | 894 |
| LMArena Russian | 1253 | 1111 |
| LMArena Spanish | 1261 | 1111 |
Instruction Following Claude 3.5 Haiku leads
Claude 3.5 Haiku: 62.9 (#234), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 47.2% |
| LMArena Instruction Following | 1241 | 1087 |
| IFEval | 79.2% | — |
Long Context Claude 3.5 Haiku leads
Claude 3.5 Haiku: 38.3 (#200), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1261 | 1088 |
Writing & Preference Claude 3.5 Haiku leads
Claude 3.5 Haiku: 42.7 (#234), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Claude 3.5 Haiku | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1255 | 1110 |
| LMArena Creative Writing | 1233 | 1083 |
| LMArena Multi-Turn | 1265 | 1068 |
| LiveBench Language | 35.4% | 12.9% |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Phi 3 Small 8k Instruct?
Claude 3.5 Haiku and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (29.2 vs 29.3), so choose on price, context window or the category you care about most.
Is Claude 3.5 Haiku or Phi 3 Small 8k Instruct better for coding?
Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 27.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Phi 3 Small 8k Instruct share?
25 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Phi 3 Small 8k Instruct has 32.