Model comparison
gpt-oss-20b vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 32.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. gpt-oss-20b scores higher in 2 categories and Olmo 3 32b Think in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.1 to 35.5.
Side by side
| gpt-oss-20b | Olmo 3 32b Think | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 32.5 | 38.7 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-20b: 37.6 (#192), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1306 | 1319 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Olmo 3 32b Think: —
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Olmo 3 32b Think leads
gpt-oss-20b: 19.3 (#261), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1302 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1317 | 1316 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge Too close to call
gpt-oss-20b: 34.6 (#195), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1258 | 1273 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual Too close to call
gpt-oss-20b: 42.2 (#197), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1268 | 1255 |
| LMArena Chinese | 1314 | 1300 |
| LMArena German | 1255 | 1290 |
| LMArena Russian | 1278 | 1254 |
| LMArena French | — | 1291 |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Olmo 3 32b Think leads
gpt-oss-20b: 61.8 (#240), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1236 | 1275 |
| IFEval | 73.2% | — |
Long Context Olmo 3 32b Think leads
gpt-oss-20b: 37.9 (#209), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1250 | 1296 |
Writing & Preference Olmo 3 32b Think leads
gpt-oss-20b: 35.5 (#265), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | gpt-oss-20b | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1287 | 1300 |
| LMArena Creative Writing | 1201 | 1256 |
| LMArena Multi-Turn | 1268 | 1290 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 32.5 on the Noometry Index.
Is gpt-oss-20b or Olmo 3 32b Think better for coding?
They score almost the same on coding (37.6 vs 38.6); test both on your own repository before choosing.
How many benchmarks do gpt-oss-20b and Olmo 3 32b Think share?
13 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Olmo 3 32b Think has 14.