Model comparison
Olmo 3.1 32b Think vs phi-3-medium 14B
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)
MicrosoftSummary
- The widest gap is in knowledge, where Olmo 3.1 32b Think leads 35.7 to 9.1.
Side by side
| Olmo 3.1 32b Think | phi-3-medium 14B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 37.9 | 29.7 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Olmo 3.1 32b Think: 37.7 (#189), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1291 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Olmo 3.1 32b Think: 25.2 (#150), phi-3-medium 14B: —
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1272 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 36.3 (#168), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1305 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 35.7 (#181), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1295 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Olmo 3.1 32b Think: 38.1 (#231), phi-3-medium 14B: —
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1209 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1260 | — |
| LMArena German | 1262 | — |
| LMArena Russian | 1193 | — |
| LMArena Spanish | 1289 | — |
Instruction Following Not comparable
Olmo 3.1 32b Think: 65.6 (#218), phi-3-medium 14B: —
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1247 | — |
Long Context Not comparable
Olmo 3.1 32b Think: 38.6 (#195), phi-3-medium 14B: —
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1272 | — |
Writing & Preference Not comparable
Olmo 3.1 32b Think: 46.2 (#220), phi-3-medium 14B: —
| Benchmark | Olmo 3.1 32b Think | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1226 | — |
| LMArena Multi-Turn | 1252 | — |
Frequently asked questions
Is Olmo 3.1 32b Think better than phi-3-medium 14B?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.7 on the Noometry Index.
Is Olmo 3.1 32b Think or phi-3-medium 14B better for coding?
They score almost the same on coding (37.7 vs 36.8); test both on your own repository before choosing.
How many benchmarks do Olmo 3.1 32b Think and phi-3-medium 14B share?
0 benchmarks have published results for both models. Olmo 3.1 32b Think has 15 scored results on Noometry and phi-3-medium 14B has 13.