Model comparison
o3 vs Olmo 2 0325 32b Instruct
o3 is the stronger model overall, scoring 47.5 to 32.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. o3 scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 19.5.
- The biggest single-benchmark swing is Omni-MATH: 71.4% for o3 and 16.1% for Olmo 2 0325 32b Instruct.
- Olmo 2 0325 32b Instruct has downloadable open weights; the other is API-only.
Side by side
| o3 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 47.5 | 32.7 |
| Released | 2025-04-16 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 63 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1408 | 1210 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Olmo 2 0325 32b Instruct: —
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1208 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.86 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 71.4% | 16.1% |
| LMArena Math | 1426 | 1208 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 85.9% | 41.4% |
| GPQA (HELM) | 75.3% | 28.7% |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| Confabulations | 14.4% | — |
| LMArena Expert | 1402 | — |
Multimodal Not comparable
o3: 41.4 (#36), Olmo 2 0325 32b Instruct: —
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1401 | 1160 |
| LMArena Chinese | 1437 | 1192 |
| LMArena Russian | 1406 | 1187 |
| LMArena French | 1430 | — |
| LMArena German | 1420 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
| LMArena Spanish | 1395 | — |
Instruction Following o3 leads
o3: 72.8 (#127), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 86.9% | 78% |
| LMArena Instruction Following | 1368 | 1186 |
Long Context o3 leads
o3: 53.3 (#6), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1372 | 1194 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | o3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1410 | 1218 |
| LMArena Creative Writing | 1359 | 1199 |
| WildBench | 86.1% | 73.4% |
| LMArena Multi-Turn | 1405 | 1221 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
Frequently asked questions
Is o3 better than Olmo 2 0325 32b Instruct?
o3 is the stronger model overall, scoring 47.5 to 32.7 on the Noometry Index.
Is o3 or Olmo 2 0325 32b Instruct better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 35.2 in the Noometry coding category.
How many benchmarks do o3 and Olmo 2 0325 32b Instruct share?
16 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.