Model comparison
gpt-oss-120b vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 36.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. gpt-oss-120b scores higher in 4 categories and Olmo 3 32b Think in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 33.8.
Side by side
| gpt-oss-120b | Olmo 3 32b Think | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 36.0 | 38.1 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
gpt-oss-120b: 33.2 (#251), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1380 | 1318 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Olmo 3 32b Think: —
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Olmo 3 32b Think leads
gpt-oss-120b: 19.5 (#236), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1302 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.94 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1388 | 1315 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1356 | 1272 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.2 (#142), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1350 | 1255 |
| LMArena Chinese | 1384 | 1300 |
| LMArena French | 1370 | 1291 |
| LMArena German | 1355 | 1290 |
| LMArena Russian | 1343 | 1255 |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1283 | — |
| LMArena Spanish | 1388 | — |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.5 (#168), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1318 | 1275 |
| IFEval | 83.6% | — |
Long Context Olmo 3 32b Think leads
gpt-oss-120b: 31.4 (#273), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1319 | 1296 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Olmo 3 32b Think leads
gpt-oss-120b: 46.7 (#213), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | gpt-oss-120b | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1366 | 1300 |
| LMArena Creative Writing | 1274 | 1256 |
| LMArena Multi-Turn | 1340 | 1289 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 36.0 on the Noometry Index.
Is gpt-oss-120b or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 33.2 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and Olmo 3 32b Think share?
14 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Olmo 3 32b Think has 14.