# gpt-oss-20b vs Olmo 2 0325 32b Instruct

> gpt-oss-20b and Olmo 2 0325 32b Instruct score almost the same on the Noometry Index (32.5 vs 32.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-oss-20b-vs-olmo-2-0325-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. gpt-oss-20b scores higher in 6 categories and Olmo 2 0325 32b Instruct in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where gpt-oss-20b leads 34.6 to 19.5.
- The biggest single-benchmark swing is Omni-MATH: 56.5% for gpt-oss-20b and 16.1% for Olmo 2 0325 32b Instruct.

## Snapshot

| | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 32.5 | 32.7 |
| Rank | 255 | 254 |
| Context | 131K | — |
| Input $/M | $0.018 | — |
| Output $/M | $0.09 | — |
| Weights | Open | Open |

## Coding

- gpt-oss-20b: 37.6 (#192)
- Olmo 2 0325 32b Instruct: 35.2 (#227)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1306 | 1210 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |

## Agentic & Tool Use

- gpt-oss-20b: 9.3 (#154)
- Olmo 2 0325 32b Instruct: —

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| Terminal-Bench | 3.4% | — |

## Reasoning

- gpt-oss-20b: 19.3 (#261)
- Olmo 2 0325 32b Instruct: 23.6 (#175)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1208 |
| 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: 39.4 (#103)
- Olmo 2 0325 32b Instruct: 26.8 (#255)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 56.5% | 16.1% |
| LMArena Math | 1317 | 1208 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |

## Knowledge

- gpt-oss-20b: 34.6 (#195)
- Olmo 2 0325 32b Instruct: 19.5 (#279)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 74% | 41.4% |
| GPQA (HELM) | 59.4% | 28.7% |
| GPQA Diamond | 60.8% | — |
| LMArena Expert | 1258 | — |

## Multilingual

- gpt-oss-20b: 42.2 (#197)
- Olmo 2 0325 32b Instruct: 34.8 (#248)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1160 |
| LMArena Chinese | 1314 | 1192 |
| LMArena Russian | 1278 | 1187 |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Spanish | 1267 | — |

## Instruction Following

- gpt-oss-20b: 61.8 (#240)
- Olmo 2 0325 32b Instruct: 61.5 (#244)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 73.2% | 78% |
| LMArena Instruction Following | 1236 | 1186 |

## Long Context

- gpt-oss-20b: 37.9 (#209)
- Olmo 2 0325 32b Instruct: 36.2 (#234)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1250 | 1194 |

## Writing & Preference

- gpt-oss-20b: 35.5 (#265)
- Olmo 2 0325 32b Instruct: 42.1 (#236)

| Benchmark | gpt-oss-20b | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1287 | 1218 |
| LMArena Creative Writing | 1201 | 1199 |
| WildBench | 73.7% | 73.4% |
| LMArena Multi-Turn | 1268 | 1221 |
| EQ-Bench Creative Writing | 666 | — |

## FAQ

### Is gpt-oss-20b better than Olmo 2 0325 32b Instruct?

gpt-oss-20b and Olmo 2 0325 32b Instruct score almost the same on the Noometry Index (32.5 vs 32.7), so choose on price, context window or the category you care about most.

### Is gpt-oss-20b or Olmo 2 0325 32b Instruct better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 35.2 in the Noometry coding category.

### How many benchmarks do gpt-oss-20b and Olmo 2 0325 32b Instruct share?

16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.