Model comparison
Olmo 7b Instruct vs Phi 3 Small 8k Instruct
Olmo 7b Instruct is the stronger model overall, scoring 30.3 to 29.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)
MicrosoftSummary
- They share 10 benchmarks with published results for both. Olmo 7b Instruct scores higher in 3 categories and Phi 3 Small 8k Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Small 8k Instruct leads 31.1 to 25.8.
Side by side
| Olmo 7b Instruct | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 30.3 | 29.3 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 7b Instruct leads
Olmo 7b Instruct: 29.6 (#303), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1016 | 1101 |
| LiveBench Coding | — | 20.3% |
Reasoning Olmo 7b Instruct leads
Olmo 7b Instruct: 18.8 (#274), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 993 | 1100 |
| 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 Olmo 7b Instruct leads
Olmo 7b Instruct: 30.2 (#237), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1018 | 1151 |
| LiveBench Math | — | 17.6% |
Knowledge Not comparable
Olmo 7b Instruct: —, Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | — | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Phi 3 Small 8k Instruct leads
Olmo 7b Instruct: 24.0 (#291), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 977 | 1058 |
| LMArena Chinese | 1014 | 1061 |
| LMArena Russian | 947 | 1111 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Spanish | — | 1111 |
Instruction Following Phi 3 Small 8k Instruct leads
Olmo 7b Instruct: 49.0 (#301), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 978 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Not comparable
Olmo 7b Instruct: —, Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1088 |
Writing & Preference Phi 3 Small 8k Instruct leads
Olmo 7b Instruct: 25.8 (#303), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Olmo 7b Instruct | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1032 | 1110 |
| LMArena Creative Writing | 990 | 1083 |
| LMArena Multi-Turn | 1007 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Olmo 7b Instruct better than Phi 3 Small 8k Instruct?
Olmo 7b Instruct is the stronger model overall, scoring 30.3 to 29.3 on the Noometry Index.
Is Olmo 7b Instruct or Phi 3 Small 8k Instruct better for coding?
Olmo 7b Instruct scores higher on coding benchmarks: 29.6 versus 27.9 in the Noometry coding category.
How many benchmarks do Olmo 7b Instruct and Phi 3 Small 8k Instruct share?
10 benchmarks have published results for both models. Olmo 7b Instruct has 10 scored results on Noometry and Phi 3 Small 8k Instruct has 32.