Model comparison
gpt-oss-20b vs Phi 3 Mini 128k Instruct
gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.1 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 Mini 128k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.4 to 25.4.
Side by side
| gpt-oss-20b | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 32.1 | 29.1 |
| 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 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.1 (#185), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1307 | 1040 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Phi 3 Mini 128k Instruct: —
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Too close to call
gpt-oss-20b: 18.8 (#251), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1028 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 37.6 (#93), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1317 | 1089 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#186), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1258 | 984 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.4 (#192), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1269 | 1000 |
| LMArena Chinese | 1311 | 1016 |
| LMArena German | 1249 | 1006 |
| LMArena Japanese | 1245 | 899 |
| LMArena Korean | 1239 | 856 |
| LMArena Russian | 1279 | 1004 |
| LMArena Spanish | 1267 | 1058 |
| LMArena French | — | 1038 |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 62.0 (#235), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1236 | 1023 |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#203), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1251 | 996 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.8 (#260), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | gpt-oss-20b | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1288 | 1050 |
| LMArena Creative Writing | 1201 | 1024 |
| LMArena Multi-Turn | 1268 | 989 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Phi 3 Mini 128k Instruct?
gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.1 on the Noometry Index.
Is gpt-oss-20b or Phi 3 Mini 128k Instruct better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 28.3 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Phi 3 Mini 128k Instruct share?
16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.