Model comparison
gpt-oss-20b vs OLMo 2 Furious 13B
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.7 on the Noometry Index.
Last verified . 5 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 5 benchmarks with published results for both. gpt-oss-20b scores higher in 5 categories and OLMo 2 Furious 13B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 23.1.
- The biggest single-benchmark swing is MMLU-Pro: 74% for gpt-oss-20b and 31% for OLMo 2 Furious 13B.
Side by side
| gpt-oss-20b | OLMo 2 Furious 13B | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 32.5 | 29.7 |
| Released | 2025-08-05 | 2024-12-31 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), OLMo 2 Furious 13B: 28.6 (#313)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LiveBench Coding | — | 10.4% |
| LMArena Coding | 1306 | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), OLMo 2 Furious 13B: —
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning gpt-oss-20b leads
gpt-oss-20b: 19.3 (#261), OLMo 2 Furious 13B: 15.5 (#314)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LiveBench Reasoning | — | 16.3% |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LiveBench Data Analysis | — | 20.6% |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
| LiveBench | — | 22.1% |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), OLMo 2 Furious 13B: 23.1 (#273)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| Omni-MATH | 56.5% | 15.6% |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| LiveBench Math | — | 13.6% |
| LMArena Math | 1317 | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), OLMo 2 Furious 13B: 18.3 (#283)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| MMLU-Pro | 74% | 31% |
| GPQA (HELM) | 59.4% | 31.6% |
| GPQA Diamond | 60.8% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.2 (#197), OLMo 2 Furious 13B: —
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Non-English | 1268 | — |
| LMArena Chinese | 1314 | — |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Too close to call
gpt-oss-20b: 61.8 (#240), OLMo 2 Furious 13B: 60.9 (#248)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| IFEval | 73.2% | 73% |
| LiveBench Instruction Following | — | 60.6% |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#209), OLMo 2 Furious 13B: —
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| LMArena Longer Query | 1250 | — |
Writing & Preference OLMo 2 Furious 13B leads
gpt-oss-20b: 35.5 (#265), OLMo 2 Furious 13B: 42.9 (#230)
| Benchmark | gpt-oss-20b | OLMo 2 Furious 13B |
|---|---|---|
| WildBench | 73.7% | 68.9% |
| LMArena Text | 1287 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| LMArena Multi-Turn | 1268 | — |
| LiveBench Language | — | 11.2% |
Frequently asked questions
Is gpt-oss-20b better than OLMo 2 Furious 13B?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.7 on the Noometry Index.
Is gpt-oss-20b or OLMo 2 Furious 13B better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 28.6 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and OLMo 2 Furious 13B share?
5 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and OLMo 2 Furious 13B has 12.