Model comparison
gpt-oss-20b vs Phi-2
gpt-oss-20b has enough public results to be ranked (#249); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both.
Side by side
| gpt-oss-20b | Phi-2 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 32.1 | — |
| Released | 2025-08-05 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
gpt-oss-20b: 37.1 (#185), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1307 | — |
| ALE-Bench | 566.05 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Not comparable
gpt-oss-20b: 18.8 (#251), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 137.81 | 107.62 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
gpt-oss-20b: 37.6 (#93), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge Not comparable
gpt-oss-20b: 34.6 (#186), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
gpt-oss-20b: 42.4 (#192), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1311 | — |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Russian | 1279 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 62.0 (#235), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#203), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.8 (#260), Phi-2: —
| Benchmark | gpt-oss-20b | Phi-2 |
|---|---|---|
| LMArena Text | 1288 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Phi-2?
gpt-oss-20b has enough public results to be ranked (#249); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do gpt-oss-20b and Phi-2 share?
1 benchmark has published results for both models. gpt-oss-20b has 34 scored results on Noometry and Phi-2 has 11.