Model comparison
GPT-5 Mini vs gpt-oss-20b
GPT-5 Mini is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 19× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-5 Mini scores higher in 9 categories and gpt-oss-20b in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5 Mini leads 31.1 to 9.3.
- The biggest single-benchmark swing is Terminal-Bench: 34.8% for GPT-5 Mini and 3.4% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 41.8 | 32.5 |
| Released | 2025-08-07 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.25 | $0.018 |
| Output $ / M tokens | $2 | $0.09 |
| Results tracked | 60 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.1 (#146), gpt-oss-20b: 37.6 (#192)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| SciCode | 39.2% | 34.4% |
| WeirdML | 52.7% | 40.9% |
| LMArena Coding | 1406 | 1306 |
| ALE-Bench | 799.77 | 566.05 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.1 (#70), gpt-oss-20b: 9.3 (#154)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | 34.8% | 3.4% |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 23.9 (#168), gpt-oss-20b: 19.3 (#261)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 53.2% |
| CritPt | 0% | 1.4% |
| Chess Puzzles | 30% | 4% |
| LMArena Hard Prompts | 1380 | 1274 |
| DTBench | 80.5% | 68% |
| LMCA | 34.2% | 14.5% |
| Epoch Capabilities Index | 145.52 | 137.82 |
| ARC-AGI-2 | 4.4% | — |
| ARC-AGI-1 | 54.3% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| ForecastBench | 61 | — |
Math GPT-5 Mini leads
GPT-5 Mini: 46.7 (#69), gpt-oss-20b: 39.4 (#103)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 65.3% |
| Omni-MATH | 72.2% | 56.5% |
| LMArena Math | 1378 | 1317 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), gpt-oss-20b: 34.6 (#195)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 75% | 60.8% |
| MMLU-Pro | 83.5% | 74% |
| GPQA (HELM) | 75.6% | 59.4% |
| LMArena Expert | 1379 | 1258 |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), gpt-oss-20b: —
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), gpt-oss-20b: 42.2 (#197)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1363 | 1268 |
| LMArena Chinese | 1385 | 1314 |
| LMArena German | 1366 | 1255 |
| LMArena Japanese | 1341 | 1244 |
| LMArena Korean | 1308 | 1236 |
| LMArena Russian | 1362 | 1278 |
| LMArena Spanish | 1355 | 1267 |
| LMArena French | 1386 | — |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), gpt-oss-20b: 61.8 (#240)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| IFEval | 92.7% | 73.2% |
| LMArena Instruction Following | 1357 | 1236 |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#132), gpt-oss-20b: 37.9 (#209)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1355 | 1250 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), gpt-oss-20b: 35.5 (#265)
| Benchmark | GPT-5 Mini | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1373 | 1287 |
| LMArena Creative Writing | 1325 | 1201 |
| EQ-Bench Creative Writing | 1313 | 666 |
| WildBench | 85.5% | 73.7% |
| LMArena Multi-Turn | 1363 | 1268 |
| Short-Story Creative Writing | 83.1% | — |
Frequently asked questions
Is GPT-5 Mini better than gpt-oss-20b?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 19× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Mini or gpt-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5 Mini or gpt-oss-20b better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 131K.
How many benchmarks do GPT-5 Mini and gpt-oss-20b share?
34 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and gpt-oss-20b has 34.