Model comparison
gpt-oss-20b vs Phi 3 Small 8k Instruct
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
MicrosoftSummary
- They share 16 benchmarks with published results for both. gpt-oss-20b scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.2 to 28.5.
Side by side
| gpt-oss-20b | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 32.5 | 29.3 |
| Released | 2025-08-05 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 32 |
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), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1306 | 1101 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Phi 3 Small 8k Instruct: —
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning gpt-oss-20b leads
gpt-oss-20b: 19.3 (#261), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1100 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 68% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 14.5% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 137.82 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1317 | 1151 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| LiveBench Math | — | 17.6% |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1258 | 1067 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.2 (#197), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1058 |
| LMArena Chinese | 1314 | 1061 |
| LMArena German | 1255 | 1080 |
| LMArena Japanese | 1244 | 966 |
| LMArena Korean | 1236 | 894 |
| LMArena Russian | 1278 | 1111 |
| LMArena Spanish | 1267 | 1111 |
| LMArena French | — | 1135 |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 61.8 (#240), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1236 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#209), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1250 | 1088 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.5 (#265), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | gpt-oss-20b | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1287 | 1110 |
| LMArena Creative Writing | 1201 | 1083 |
| LMArena Multi-Turn | 1268 | 1068 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is gpt-oss-20b better than Phi 3 Small 8k Instruct?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.3 on the Noometry Index.
Is gpt-oss-20b or Phi 3 Small 8k Instruct better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 27.9 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Phi 3 Small 8k Instruct share?
16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Phi 3 Small 8k Instruct has 32.