Model comparison
o4-mini vs Olmo 3 32b Think
o4-mini is the stronger model overall, scoring 41.6 to 38.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. o4-mini scores higher in 7 categories and Olmo 3 32b Think in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.6 to 35.0.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| o4-mini | Olmo 3 32b Think | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 41.6 | 38.7 |
| Released | 2025-04-16 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $1.10 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 60 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
o4-mini: 40.9 (#127), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1368 | 1319 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use Not comparable
o4-mini: 32.6 (#61), Olmo 3 32b Think: —
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |
Reasoning Olmo 3 32b Think leads
o4-mini: 24.6 (#162), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1351 | 1302 |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 58.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LMCA | 26.5% | — |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |
Math o4-mini leads
o4-mini: 40.8 (#89), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1389 | 1316 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge o4-mini leads
o4-mini: 43.6 (#91), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1343 | 1273 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Not comparable
o4-mini: 40.2 (#49), Olmo 3 32b Think: —
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1194 | — |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual o4-mini leads
o4-mini: 47.0 (#154), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1337 | 1255 |
| LMArena Chinese | 1354 | 1300 |
| LMArena French | 1364 | 1291 |
| LMArena German | 1336 | 1290 |
| LMArena Russian | 1334 | 1254 |
| LMArena Japanese | 1308 | — |
| LMArena Korean | 1312 | — |
| LMArena Spanish | 1347 | — |
Instruction Following o4-mini leads
o4-mini: 75.2 (#68), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1321 | 1275 |
| IFEval | 92.8% | — |
Long Context o4-mini leads
o4-mini: 45.5 (#33), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1315 | 1296 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference o4-mini leads
o4-mini: 54.0 (#152), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | o4-mini | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1353 | 1300 |
| LMArena Creative Writing | 1294 | 1256 |
| LMArena Multi-Turn | 1350 | 1290 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is o4-mini better than Olmo 3 32b Think?
o4-mini is the stronger model overall, scoring 41.6 to 38.7 on the Noometry Index.
Is o4-mini or Olmo 3 32b Think better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 38.6 in the Noometry coding category.
How many benchmarks do o4-mini and Olmo 3 32b Think share?
14 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Olmo 3 32b Think has 14.