Model comparison
Phi 3 Small 8k Instruct vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.3 on the Noometry Index.
Last verified . 11 shared benchmarks.
Microsoft
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 31.1.
Side by side
| Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Microsoft | Allen Institute for AI (Ai2) |
| Noometry Index | 29.3 | 33.0 |
| Released | 2024-04-23 | 2024-11-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 27.9 (#318), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1101 | 1235 |
| LiveBench Coding | 20.3% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 14.8 (#323), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1220 |
| LiveBench Reasoning | 15.9% | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 27.6 (#248), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1151 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LiveBench Math | 17.6% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 29.1 (#240), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1067 | — |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 28.5 (#272), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1058 | 1236 |
| LMArena Chinese | 1061 | 1249 |
| LMArena Russian | 1111 | 1246 |
| LMArena French | 1135 | — |
| LMArena German | 1080 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 51.9 (#292), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1087 | 1233 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 33.0 (#267), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1088 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Phi 3 Small 8k Instruct: 31.1 (#284), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Phi 3 Small 8k Instruct | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1110 | 1256 |
| LMArena Creative Writing | 1083 | 1231 |
| LMArena Multi-Turn | 1068 | 1252 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.