Model comparison
Olmo 3 32b Think vs Phi 3 Mini 4k Instruct
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 27.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)
MicrosoftSummary
- They share 14 benchmarks with published results for both. Olmo 3 32b Think scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.2 to 27.7.
Side by side
| Olmo 3 32b Think | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 38.1 | 27.4 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Olmo 3 32b Think: 38.0 (#169), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1318 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Olmo 3 32b Think leads
Olmo 3 32b Think: 24.9 (#138), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Olmo 3 32b Think leads
Olmo 3 32b Think: 33.8 (#165), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1315 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Olmo 3 32b Think leads
Olmo 3 32b Think: 34.4 (#189), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1272 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Olmo 3 32b Think leads
Olmo 3 32b Think: 41.4 (#205), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1255 | 1021 |
| LMArena Chinese | 1300 | 1021 |
| LMArena French | 1291 | 1075 |
| LMArena German | 1290 | 1044 |
| LMArena Russian | 1255 | 1022 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Spanish | — | 1084 |
Instruction Following Olmo 3 32b Think leads
Olmo 3 32b Think: 67.4 (#193), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1275 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Olmo 3 32b Think leads
Olmo 3 32b Think: 39.4 (#177), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1296 | 1044 |
Writing & Preference Olmo 3 32b Think leads
Olmo 3 32b Think: 49.2 (#188), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Olmo 3 32b Think | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1300 | 1073 |
| LMArena Creative Writing | 1256 | 1037 |
| LMArena Multi-Turn | 1289 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Olmo 3 32b Think better than Phi 3 Mini 4k Instruct?
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 27.4 on the Noometry Index.
Is Olmo 3 32b Think or Phi 3 Mini 4k Instruct better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 26.1 in the Noometry coding category.
How many benchmarks do Olmo 3 32b Think and Phi 3 Mini 4k Instruct share?
14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.