Model comparison
gpt-oss-20b vs Phi 3 Mini 4k Instruct June 2024
gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
MicrosoftSummary
- They share 15 benchmarks with published results for both. gpt-oss-20b scores higher in 7 categories and Phi 3 Mini 4k Instruct June 2024 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.4 to 26.0.
Side by side
| gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 32.1 | 30.7 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 15 |
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 4k Instruct June 2024: 31.2 (#275)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Coding | 1307 | 1093 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.2 (#146), Phi 3 Mini 4k Instruct June 2024: —
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Phi 3 Mini 4k Instruct June 2024 leads
gpt-oss-20b: 18.8 (#251), Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1088 |
| 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 4k Instruct June 2024: 30.4 (#209)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Math | 1317 | 1152 |
| 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 4k Instruct June 2024: 28.1 (#240)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Expert | 1258 | 1051 |
| 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 4k Instruct June 2024: 26.0 (#277)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Non-English | 1269 | 1013 |
| LMArena Chinese | 1311 | 1033 |
| LMArena German | 1249 | 1031 |
| LMArena Japanese | 1245 | 954 |
| LMArena Korean | 1239 | 880 |
| LMArena Russian | 1279 | 1019 |
| LMArena Spanish | 1267 | — |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 62.0 (#235), Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1058 |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#203), Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Longer Query | 1251 | 1042 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.8 (#260), Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)
| Benchmark | gpt-oss-20b | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Text | 1288 | 1080 |
| LMArena Creative Writing | 1201 | 1045 |
| LMArena Multi-Turn | 1268 | 1049 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Phi 3 Mini 4k Instruct June 2024?
gpt-oss-20b is the stronger model overall, scoring 32.1 to 30.7 on the Noometry Index.
Is gpt-oss-20b or Phi 3 Mini 4k Instruct June 2024 better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 31.2 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Phi 3 Mini 4k Instruct June 2024 share?
15 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.